test: Added 3 audio proxy scoring functions, extract_word_timings utili…

- "backend/pipeline/highlight_scorer.py"
- "backend/pipeline/highlight_schemas.py"
- "backend/pipeline/test_highlight_scorer.py"

GSD-Task: S05/T01

backend/pipeline/highlight_schemas.py

@@ -25,6 +25,18 @@ class HighlightScoreBreakdown(BaseModel):
     uniqueness_score: float = Field(description="Score based on title/topic distinctness among siblings")
     engagement_proxy_score: float = Field(description="Proxy engagement signal from summary quality/length")
     plugin_diversity_score: float = Field(description="Score based on breadth of plugins/tools mentioned")
+    speech_rate_variance_score: float = Field(
+        default=0.5,
+        description="Score based on speech rate variation (emphasis shifts) from word timings",
+    )
+    pause_density_score: float = Field(
+        default=0.5,
+        description="Score based on strategic pause frequency from word timings",
+    )
+    speaking_pace_score: float = Field(
+        default=0.5,
+        description="Score based on words-per-second fitness for teaching pace",
+    )
 
 
 class HighlightCandidateResponse(BaseModel):

backend/pipeline/highlight_scorer.py

@@ -1,30 +1,35 @@
 """Heuristic scoring engine for highlight candidate detection.
 
 Takes KeyMoment data + context (source quality, video content type) and
-returns a composite score in [0, 1] with a 7-dimension breakdown.
+returns a composite score in [0, 1] with a 10-dimension breakdown.
 
 The breakdown fields align with HighlightScoreBreakdown in highlight_schemas.py:
   duration_score, content_density_score, technique_relevance_score,
-  position_score, uniqueness_score, engagement_proxy_score, plugin_diversity_score
+  position_score, uniqueness_score, engagement_proxy_score, plugin_diversity_score,
+  speech_rate_variance_score, pause_density_score, speaking_pace_score
 """
 
 from __future__ import annotations
 
 import math
 import re
+import statistics
 from typing import Any
 
 
 # ── Weights per dimension (must sum to 1.0) ──────────────────────────────────
 
 _WEIGHTS: dict[str, float] = {
-    "duration_score": 0.25,
+    "duration_score": 0.20,
-    "content_density_score": 0.20,
+    "content_density_score": 0.15,
-    "technique_relevance_score": 0.20,
+    "technique_relevance_score": 0.15,
-    "plugin_diversity_score": 0.10,
+    "plugin_diversity_score": 0.08,
-    "engagement_proxy_score": 0.10,
+    "engagement_proxy_score": 0.08,
-    "position_score": 0.10,          # mapped from source_quality
+    "position_score": 0.08,          # mapped from source_quality
-    "uniqueness_score": 0.05,        # mapped from video_type
+    "uniqueness_score": 0.04,        # mapped from video_type
+    "speech_rate_variance_score": 0.08,
+    "pause_density_score": 0.07,
+    "speaking_pace_score": 0.07,
 }
 
 assert abs(sum(_WEIGHTS.values()) - 1.0) < 1e-9, "Weights must sum to 1.0"
@@ -176,6 +181,163 @@ def _video_type_weight(video_content_type: str | None) -> float:
     return mapping.get(video_content_type or "", 0.5)
 
 
+# ── Audio proxy scoring functions ─────────────────────────────────────────────
+
+def extract_word_timings(
+    transcript_data: list[dict[str, Any]],
+    start_time: float,
+    end_time: float,
+) -> list[dict[str, Any]]:
+    """Extract word-level timing dicts from transcript segments within a time window.
+
+    Parameters
+    ----------
+    transcript_data : list[dict]
+        Parsed transcript JSON — list of segments, each with a ``words`` array.
+        Each word dict must have ``start`` and ``end`` float fields (seconds).
+    start_time : float
+        Window start in seconds (inclusive).
+    end_time : float
+        Window end in seconds (inclusive).
+
+    Returns
+    -------
+    list[dict] — word-timing dicts whose ``start`` falls within [start_time, end_time].
+    """
+    if not transcript_data:
+        return []
+
+    words: list[dict[str, Any]] = []
+    for segment in transcript_data:
+        seg_words = segment.get("words")
+        if not seg_words:
+            continue
+        for w in seg_words:
+            w_start = w.get("start")
+            if w_start is None:
+                continue
+            if start_time <= w_start <= end_time:
+                words.append(w)
+    return words
+
+
+def _speech_rate_variance(word_timings: list[dict[str, Any]] | None) -> float:
+    """Compute normalized stdev of words-per-second in sliding windows.
+
+    High variance indicates emphasis shifts (speeding up / slowing down),
+    which correlates with engaging highlights.
+
+    Uses 5-second sliding windows with 2.5-second step.
+    Returns 0.5 (neutral) when word_timings is None or insufficient data.
+    """
+    if not word_timings or len(word_timings) < 4:
+        return 0.5
+
+    # Determine time span
+    first_start = word_timings[0].get("start", 0.0)
+    last_start = word_timings[-1].get("start", 0.0)
+    span = last_start - first_start
+    if span < 5.0:
+        return 0.5
+
+    # Compute WPS in 5s sliding windows with 2.5s step
+    window_size = 5.0
+    step = 2.5
+    wps_values: list[float] = []
+
+    t = first_start
+    while t + window_size <= last_start + 0.01:
+        count = sum(
+            1 for w in word_timings
+            if t <= w.get("start", 0.0) < t + window_size
+        )
+        wps_values.append(count / window_size)
+        t += step
+
+    if len(wps_values) < 2:
+        return 0.5
+
+    mean_wps = statistics.mean(wps_values)
+    if mean_wps < 0.01:
+        return 0.5
+
+    stdev = statistics.stdev(wps_values)
+    # Normalize: coefficient of variation, capped at 1.0
+    # CV of ~0.3-0.5 is typical for varied speech; >0.5 is high variance
+    cv = stdev / mean_wps
+    return min(cv / 0.6, 1.0)
+
+
+def _pause_density(word_timings: list[dict[str, Any]] | None) -> float:
+    """Count strategic pauses normalized by duration.
+
+    Inter-word gaps >0.5s and inter-segment gaps >1.0s indicate deliberate
+    pauses for emphasis, which correlate with better highlights.
+
+    Returns 0.5 (neutral) when word_timings is None or insufficient data.
+    """
+    if not word_timings or len(word_timings) < 2:
+        return 0.5
+
+    first_start = word_timings[0].get("start", 0.0)
+    last_end = word_timings[-1].get("end", word_timings[-1].get("start", 0.0))
+    duration = last_end - first_start
+    if duration < 1.0:
+        return 0.5
+
+    short_pauses = 0  # >0.5s gaps
+    long_pauses = 0   # >1.0s gaps
+
+    for i in range(1, len(word_timings)):
+        prev_end = word_timings[i - 1].get("end", word_timings[i - 1].get("start", 0.0))
+        curr_start = word_timings[i].get("start", 0.0)
+        gap = curr_start - prev_end
+
+        if gap > 1.0:
+            long_pauses += 1
+        elif gap > 0.5:
+            short_pauses += 1
+
+    # Weight long pauses more heavily
+    weighted_pauses = short_pauses + long_pauses * 2.0
+    # Normalize: ~2-4 weighted pauses per 30s is good density
+    density = weighted_pauses / (duration / 15.0)
+    return min(density, 1.0)
+
+
+def _speaking_pace_fitness(word_timings: list[dict[str, Any]] | None) -> float:
+    """Bell-curve score around 3-5 words-per-second optimal teaching pace.
+
+    3-5 WPS is the sweet spot for tutorial content — fast enough to be
+    engaging, slow enough for comprehension. Returns 0.5 (neutral) when
+    word_timings is None or insufficient data.
+    """
+    if not word_timings or len(word_timings) < 2:
+        return 0.5
+
+    first_start = word_timings[0].get("start", 0.0)
+    last_end = word_timings[-1].get("end", word_timings[-1].get("start", 0.0))
+    duration = last_end - first_start
+    if duration < 1.0:
+        return 0.5
+
+    wps = len(word_timings) / duration
+
+    # Sweet spot: 3-5 WPS → 1.0
+    if 3.0 <= wps <= 5.0:
+        return 1.0
+
+    # Below sweet spot: linear ramp from 0 at 0 WPS to 1.0 at 3 WPS
+    if wps < 3.0:
+        return max(0.0, wps / 3.0)
+
+    # Above sweet spot: decay from 1.0 at 5 WPS to 0.0 at 10 WPS
+    if wps > 5.0:
+        return max(0.0, 1.0 - (wps - 5.0) / 5.0)
+
+    return 0.5  # unreachable, but defensive
+
+
 # ── Main scoring function ───────────────────────────────────────────────────
 
 def score_moment(
@@ -188,6 +350,7 @@ def score_moment(
     raw_transcript: str | None = None,
     source_quality: str | None = None,
     video_content_type: str | None = None,
+    word_timings: list[dict[str, Any]] | None = None,
 ) -> dict[str, Any]:
     """Score a KeyMoment for highlight potential.
 
@@ -209,6 +372,9 @@ def score_moment(
         TechniquePage source quality (structured, mixed, unstructured).
     video_content_type : str | None
         SourceVideo content type (tutorial, breakdown, livestream, short_form).
+    word_timings : list[dict] | None
+        Word-level timing dicts with ``start`` and ``end`` keys (seconds).
+        When None, audio proxy dimensions score 0.5 (neutral).
 
     Returns
     -------
@@ -227,6 +393,9 @@ def score_moment(
         "engagement_proxy_score": _transcript_energy(raw_transcript),
         "position_score": _source_quality_weight(source_quality),
         "uniqueness_score": _video_type_weight(video_content_type),
+        "speech_rate_variance_score": _speech_rate_variance(word_timings),
+        "pause_density_score": _pause_density(word_timings),
+        "speaking_pace_score": _speaking_pace_fitness(word_timings),
     }
 
     # Weighted composite

backend/pipeline/test_highlight_scorer.py

@@ -11,11 +11,15 @@ import pytest
 from backend.pipeline.highlight_scorer import (
     _content_type_weight,
     _duration_fitness,
+    _pause_density,
     _plugin_richness,
     _source_quality_weight,
+    _speaking_pace_fitness,
     _specificity_density,
+    _speech_rate_variance,
     _transcript_energy,
     _video_type_weight,
+    extract_word_timings,
     score_moment,
 )
 
@@ -80,6 +84,50 @@ def _poor_moment() -> dict:
     )
 
 
+def _make_word_timings(
+    start: float = 0.0,
+    count: int = 40,
+    wps: float = 4.0,
+    pause_every: int | None = None,
+    pause_duration: float = 0.8,
+) -> list[dict]:
+    """Generate synthetic word-timing dicts for testing.
+
+    Parameters
+    ----------
+    start : float
+        Start time in seconds.
+    count : int
+        Number of words to generate.
+    wps : float
+        Words per second (base rate).
+    pause_every : int | None
+        Insert a pause every N words. None = no pauses.
+    pause_duration : float
+        Duration of each pause in seconds.
+    """
+    timings = []
+    t = start
+    word_dur = 1.0 / wps * 0.7  # 70% speaking, 30% normal gap
+    gap = 1.0 / wps * 0.3
+
+    for i in range(count):
+        timings.append({"word": f"word{i}", "start": t, "end": t + word_dur})
+        t += word_dur + gap
+        if pause_every and (i + 1) % pause_every == 0:
+            t += pause_duration
+    return timings
+
+
+def _make_transcript_segments(word_timings: list[dict], words_per_segment: int = 10) -> list[dict]:
+    """Group word timings into transcript segments for extract_word_timings tests."""
+    segments = []
+    for i in range(0, len(word_timings), words_per_segment):
+        chunk = word_timings[i : i + words_per_segment]
+        segments.append({"words": chunk})
+    return segments
+
+
 # ── Tests ────────────────────────────────────────────────────────────────────
 
 class TestScoreMoment:
@@ -130,22 +178,41 @@ class TestScoreMoment:
         )
         assert 0.0 <= result["score"] <= 1.0
         assert result["duration_secs"] == 45.0
-        assert len(result["score_breakdown"]) == 7
+        assert len(result["score_breakdown"]) == 10
 
     def test_returns_duration_secs(self):
         result = score_moment(start_time=10.0, end_time=55.0)
         assert result["duration_secs"] == 45.0
 
-    def test_breakdown_has_seven_dimensions(self):
+    def test_breakdown_has_ten_dimensions(self):
         result = score_moment(**_ideal_moment())
-        assert len(result["score_breakdown"]) == 7
+        assert len(result["score_breakdown"]) == 10
         expected_keys = {
             "duration_score", "content_density_score", "technique_relevance_score",
             "plugin_diversity_score", "engagement_proxy_score", "position_score",
-            "uniqueness_score",
+            "uniqueness_score", "speech_rate_variance_score", "pause_density_score",
+            "speaking_pace_score",
         }
         assert set(result["score_breakdown"].keys()) == expected_keys
 
+    def test_without_word_timings_audio_dims_are_neutral(self):
+        """When word_timings is None, audio proxy dimensions score 0.5."""
+        result = score_moment(start_time=10.0, end_time=55.0)
+        bd = result["score_breakdown"]
+        assert bd["speech_rate_variance_score"] == 0.5
+        assert bd["pause_density_score"] == 0.5
+        assert bd["speaking_pace_score"] == 0.5
+
+    def test_with_word_timings_changes_score(self):
+        """Providing word_timings should shift the composite score vs without."""
+        base = _ideal_moment()
+        without = score_moment(**base)
+        # Add word timings at a good teaching pace (~4 WPS) with some pauses
+        timings = _make_word_timings(start=10.0, count=120, wps=4.0, pause_every=15)
+        with_timings = score_moment(**base, word_timings=timings)
+        # Scores should differ since audio dims are no longer neutral
+        assert with_timings["score"] != without["score"]
+
 
 class TestDurationFitness:
     def test_bell_curve_peak(self):
@@ -242,3 +309,213 @@ class TestVideoTypeWeight:
 
     def test_none_default(self):
         assert _video_type_weight(None) == 0.5
+
+
+# ── Audio proxy function tests ───────────────────────────────────────────────
+
+
+class TestExtractWordTimings:
+    def test_filters_by_time_window(self):
+        words = _make_word_timings(start=0.0, count=40, wps=4.0)
+        segments = _make_transcript_segments(words)
+        # Extract window 2.0–5.0s
+        result = extract_word_timings(segments, start_time=2.0, end_time=5.0)
+        for w in result:
+            assert 2.0 <= w["start"] <= 5.0
+
+    def test_returns_all_when_window_covers_entire_range(self):
+        words = _make_word_timings(start=0.0, count=20, wps=4.0)
+        segments = _make_transcript_segments(words)
+        result = extract_word_timings(segments, start_time=0.0, end_time=100.0)
+        assert len(result) == 20
+
+    def test_empty_transcript_data(self):
+        assert extract_word_timings([], start_time=0.0, end_time=10.0) == []
+
+    def test_no_words_in_window(self):
+        words = _make_word_timings(start=0.0, count=10, wps=4.0)
+        segments = _make_transcript_segments(words)
+        # Window far beyond the word timings
+        result = extract_word_timings(segments, start_time=100.0, end_time=200.0)
+        assert result == []
+
+    def test_segments_without_words_key(self):
+        """Segments missing 'words' are skipped gracefully."""
+        segments = [{"text": "hello"}, {"words": [{"start": 1.0, "end": 1.2, "word": "a"}]}]
+        result = extract_word_timings(segments, start_time=0.0, end_time=10.0)
+        assert len(result) == 1
+
+    def test_words_without_start_are_skipped(self):
+        segments = [{"words": [{"end": 1.2, "word": "a"}, {"start": 2.0, "end": 2.2, "word": "b"}]}]
+        result = extract_word_timings(segments, start_time=0.0, end_time=10.0)
+        assert len(result) == 1
+        assert result[0]["word"] == "b"
+
+
+class TestSpeechRateVariance:
+    def test_none_returns_neutral(self):
+        assert _speech_rate_variance(None) == 0.5
+
+    def test_too_few_words_returns_neutral(self):
+        timings = _make_word_timings(count=3, wps=4.0)
+        assert _speech_rate_variance(timings) == 0.5
+
+    def test_short_span_returns_neutral(self):
+        """Words spanning <5s should return neutral."""
+        timings = _make_word_timings(count=10, wps=4.0, start=0.0)
+        # 10 words at 4 WPS = 2.5s span → too short
+        assert _speech_rate_variance(timings) == 0.5
+
+    def test_uniform_pace_scores_low(self):
+        """Steady 4 WPS for 30s → low variance."""
+        timings = _make_word_timings(start=0.0, count=120, wps=4.0)
+        score = _speech_rate_variance(timings)
+        assert score < 0.4, f"Uniform pace scored {score}, expected < 0.4"
+
+    def test_varied_pace_scores_higher(self):
+        """Alternating fast/slow sections → higher variance."""
+        timings = []
+        t = 0.0
+        # Fast section: 6 WPS for 10s
+        for i in range(60):
+            dur = 0.12
+            timings.append({"word": f"w{i}", "start": t, "end": t + dur})
+            t += 1.0 / 6.0
+        # Slow section: 2 WPS for 10s
+        for i in range(20):
+            dur = 0.3
+            timings.append({"word": f"w{60+i}", "start": t, "end": t + dur})
+            t += 0.5
+        score = _speech_rate_variance(timings)
+        uniform_score = _speech_rate_variance(
+            _make_word_timings(start=0.0, count=80, wps=4.0)
+        )
+        assert score > uniform_score, (
+            f"Varied pace ({score:.3f}) should be > uniform ({uniform_score:.3f})"
+        )
+
+    def test_score_bounded(self):
+        timings = _make_word_timings(start=0.0, count=200, wps=4.0)
+        score = _speech_rate_variance(timings)
+        assert 0.0 <= score <= 1.0
+
+
+class TestPauseDensity:
+    def test_none_returns_neutral(self):
+        assert _pause_density(None) == 0.5
+
+    def test_single_word_returns_neutral(self):
+        assert _pause_density([{"start": 0.0, "end": 0.2}]) == 0.5
+
+    def test_no_pauses_scores_zero(self):
+        """Continuous speech with no gaps >0.5s → 0."""
+        timings = _make_word_timings(start=0.0, count=60, wps=4.0)
+        score = _pause_density(timings)
+        assert score == 0.0
+
+    def test_frequent_pauses_scores_high(self):
+        """Pauses every 5 words → high density."""
+        timings = _make_word_timings(start=0.0, count=60, wps=4.0, pause_every=5, pause_duration=0.8)
+        score = _pause_density(timings)
+        assert score > 0.5, f"Frequent pauses scored {score}, expected > 0.5"
+
+    def test_long_pauses_weighted_more(self):
+        """One 1.5s pause should score higher than one 0.6s pause in a longer segment."""
+        # Build timings with one long pause at midpoint — 60 words for longer duration
+        long_pause = []
+        t = 0.0
+        for i in range(60):
+            long_pause.append({"word": f"w{i}", "start": t, "end": t + 0.15})
+            t += 0.25
+            if i == 29:
+                t += 1.5  # long pause >1.0s
+        # Build timings with one short pause — same word count
+        short_pause = []
+        t = 0.0
+        for i in range(60):
+            short_pause.append({"word": f"w{i}", "start": t, "end": t + 0.15})
+            t += 0.25
+            if i == 29:
+                t += 0.6  # short pause >0.5s but <1.0s
+        assert _pause_density(long_pause) > _pause_density(short_pause)
+
+    def test_score_bounded(self):
+        timings = _make_word_timings(start=0.0, count=60, wps=4.0, pause_every=3, pause_duration=1.5)
+        score = _pause_density(timings)
+        assert 0.0 <= score <= 1.0
+
+
+class TestSpeakingPaceFitness:
+    def test_none_returns_neutral(self):
+        assert _speaking_pace_fitness(None) == 0.5
+
+    def test_single_word_returns_neutral(self):
+        assert _speaking_pace_fitness([{"start": 0.0, "end": 0.2}]) == 0.5
+
+    def test_optimal_pace_scores_high(self):
+        """4 WPS (optimal teaching pace) → 1.0."""
+        timings = _make_word_timings(start=0.0, count=40, wps=4.0)
+        score = _speaking_pace_fitness(timings)
+        assert score == 1.0, f"4 WPS scored {score}, expected 1.0"
+
+    def test_three_wps_is_sweet_spot_edge(self):
+        timings = _make_word_timings(start=0.0, count=30, wps=3.0)
+        score = _speaking_pace_fitness(timings)
+        assert score == 1.0
+
+    def test_five_wps_is_sweet_spot_edge(self):
+        timings = _make_word_timings(start=0.0, count=50, wps=5.0)
+        score = _speaking_pace_fitness(timings)
+        assert score > 0.95, f"5 WPS scored {score}, expected near 1.0"
+
+    def test_too_slow_scores_lower(self):
+        """1.5 WPS → below sweet spot."""
+        timings = _make_word_timings(start=0.0, count=15, wps=1.5)
+        score = _speaking_pace_fitness(timings)
+        assert 0.4 < score < 0.6, f"1.5 WPS scored {score}, expected ~0.5"
+
+    def test_too_fast_scores_lower(self):
+        """8 WPS → above sweet spot."""
+        timings = _make_word_timings(start=0.0, count=80, wps=8.0)
+        score = _speaking_pace_fitness(timings)
+        assert 0.0 < score < 1.0
+
+    def test_very_fast_scores_zero(self):
+        """10+ WPS → 0."""
+        timings = _make_word_timings(start=0.0, count=110, wps=11.0)
+        score = _speaking_pace_fitness(timings)
+        assert score == 0.0
+
+    def test_zero_wps_scores_zero(self):
+        """Very short duration → neutral."""
+        timings = [{"start": 0.0, "end": 0.01}, {"start": 0.005, "end": 0.015}]
+        score = _speaking_pace_fitness(timings)
+        # Duration ~0.015s → too short → 0.5 (neutral)
+        assert score == 0.5
+
+    def test_score_bounded(self):
+        for wps in [0.5, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 8.0, 10.0]:
+            timings = _make_word_timings(start=0.0, count=max(10, int(wps * 10)), wps=wps)
+            score = _speaking_pace_fitness(timings)
+            assert 0.0 <= score <= 1.0, f"WPS {wps} scored {score} out of bounds"
+
+
+class TestBackwardCompatibility:
+    """Ensure the weight rebalancing doesn't break existing relative orderings."""
+
+    def test_ideal_still_beats_poor(self):
+        ideal = score_moment(**_ideal_moment())
+        poor = score_moment(**_poor_moment())
+        assert ideal["score"] > poor["score"]
+
+    def test_ideal_still_above_threshold(self):
+        result = score_moment(**_ideal_moment())
+        assert result["score"] > 0.6, f"Ideal scored {result['score']}, expected > 0.6"
+
+    def test_poor_still_below_threshold(self):
+        result = score_moment(**_poor_moment())
+        assert result["score"] < 0.45, f"Poor scored {result['score']}, expected < 0.45"
+
+    def test_weights_sum_to_one(self):
+        from backend.pipeline.highlight_scorer import _WEIGHTS
+        assert abs(sum(_WEIGHTS.values()) - 1.0) < 1e-9