fix(voice): drop playback-phase barge transcripts that echo Hermes' own TTS
The full-duplex barge-in listener added in 5081551f0 stays active during
TTS playback with no acoustic echo cancellation. On some speaker/mic
combinations, TTS bleed alone crosses the barge threshold, gets
transcribed, and is queued as the next user turn -- whose reply is then
spoken, captured, and queued again, producing an unbounded TTS -> STT ->
TTS feedback loop (#75780).
Add a fail-closed transcript-level guard: when a barge trip happens during
the playback phase, compare the captured transcript against the TTS text
Hermes just spoke (tools/voice_mode.is_tts_echo, a language-agnostic
character-level similarity ratio). A close match is dropped instead of
queued, and the mic is handed back to the normal continuous-listening
loop. Generation-phase trips (no TTS playing, so no bleed is possible)
are unaffected.
This commit is contained in:
@@ -9,6 +9,7 @@ Dependencies (optional):
|
||||
or: uv sync --extra voice
|
||||
"""
|
||||
|
||||
import difflib
|
||||
import logging
|
||||
import math
|
||||
import os
|
||||
@@ -1310,6 +1311,43 @@ def is_voice_stop_phrase(transcript: str, stop_phrases: Optional[tuple] = None)
|
||||
return cleaned in stop_phrases
|
||||
|
||||
|
||||
# Similarity ratio (difflib.SequenceMatcher, 0..1) above which a
|
||||
# playback-phase barge transcript is treated as a self-capture of Hermes'
|
||||
# own just-spoken TTS rather than genuine user speech. See #75780: the
|
||||
# full-duplex listener has no acoustic echo cancellation, so speaker bleed
|
||||
# on the mic can trip the barge trigger and get transcribed nearly
|
||||
# verbatim from the TTS text, creating a TTS -> STT -> TTS feedback loop.
|
||||
DEFAULT_TTS_ECHO_SIMILARITY_THRESHOLD = 0.6
|
||||
|
||||
|
||||
def _normalize_for_echo_compare(text: str) -> str:
|
||||
return re.sub(r"\s+", " ", text).strip().lower()
|
||||
|
||||
|
||||
def is_tts_echo(
|
||||
transcript: str,
|
||||
spoken_text: str,
|
||||
threshold: float = DEFAULT_TTS_ECHO_SIMILARITY_THRESHOLD,
|
||||
) -> bool:
|
||||
"""Return True when *transcript* looks like a self-capture of *spoken_text*.
|
||||
|
||||
Compares a playback-phase barge-in transcript against the TTS text
|
||||
Hermes just spoke using a character-level similarity ratio, which works
|
||||
across languages without word-tokenization. A genuine user interjection
|
||||
is very unlikely to closely match Hermes' own words, so a high ratio is
|
||||
a strong signal of speaker-bleed self-capture (fail-closed guard for the
|
||||
playback-phase full-duplex listener, which has no acoustic echo
|
||||
cancellation; see #75780).
|
||||
"""
|
||||
if not transcript or not spoken_text:
|
||||
return False
|
||||
a = _normalize_for_echo_compare(transcript)
|
||||
b = _normalize_for_echo_compare(spoken_text)
|
||||
if not a or not b:
|
||||
return False
|
||||
return difflib.SequenceMatcher(None, a, b).ratio() >= threshold
|
||||
|
||||
|
||||
def voice_stop_hint() -> str:
|
||||
"""One-line 'Say "stop" to end the voice chat.' hint for voice-mode start.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user