84 lines
2.9 KiB
Python
84 lines
2.9 KiB
Python
|
"""Utterance detection: adaptive energy VAD with hangover.
|
||
|
|
|
||
|
|
Deliberately simple and dependency-free; swap for silero/webrtcvad later if the
|
||
|
|
Phase-0 PoC shows it is needed. Operates on 20 ms SLIN frames.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from __future__ import annotations
|
||
|
|
|
||
|
|
from dataclasses import dataclass, field
|
||
|
|
|
||
|
|
from gogo.voice.audio import FRAME_MS, rms
|
||
|
|
|
||
|
|
|
||
|
|
@dataclass
|
||
|
|
class VadConfig:
|
||
|
|
# energy threshold = max(min_threshold, noise_floor * ratio)
|
||
|
|
min_threshold: int = 500
|
||
|
|
noise_ratio: float = 3.0
|
||
|
|
start_ms: int = 120 # this much voiced audio starts an utterance
|
||
|
|
end_ms: int = 700 # this much silence ends it
|
||
|
|
max_utterance_ms: int = 15000 # hard cap
|
||
|
|
pre_roll_ms: int = 200 # audio kept from before the trigger
|
||
|
|
|
||
|
|
|
||
|
|
@dataclass
|
||
|
|
class UtteranceCollector:
|
||
|
|
"""Feed 20 ms frames; returns the full utterance PCM when one completes."""
|
||
|
|
|
||
|
|
config: VadConfig = field(default_factory=VadConfig)
|
||
|
|
_noise_floor: float = 200.0
|
||
|
|
_voiced_ms: int = 0
|
||
|
|
_silence_ms: int = 0
|
||
|
|
_in_utterance: bool = False
|
||
|
|
_buffer: bytearray = field(default_factory=bytearray)
|
||
|
|
_pre_roll: bytearray = field(default_factory=bytearray)
|
||
|
|
|
||
|
|
def is_speech(self, frame: bytes) -> bool:
|
||
|
|
energy = rms(frame)
|
||
|
|
threshold = max(self.config.min_threshold, self._noise_floor * self.config.noise_ratio)
|
||
|
|
speech = energy > threshold
|
||
|
|
if not speech:
|
||
|
|
# slowly track the noise floor on non-speech frames
|
||
|
|
self._noise_floor = 0.95 * self._noise_floor + 0.05 * energy
|
||
|
|
return speech
|
||
|
|
|
||
|
|
def feed(self, frame: bytes) -> bytes | None:
|
||
|
|
"""Returns utterance PCM when a complete utterance is detected, else None."""
|
||
|
|
speech = self.is_speech(frame)
|
||
|
|
|
||
|
|
if not self._in_utterance:
|
||
|
|
self._pre_roll.extend(frame)
|
||
|
|
max_pre = self.config.pre_roll_ms * len(frame) // FRAME_MS
|
||
|
|
if len(self._pre_roll) > max_pre:
|
||
|
|
del self._pre_roll[: len(self._pre_roll) - max_pre]
|
||
|
|
if speech:
|
||
|
|
self._voiced_ms += FRAME_MS
|
||
|
|
if self._voiced_ms >= self.config.start_ms:
|
||
|
|
self._in_utterance = True
|
||
|
|
self._buffer = bytearray(self._pre_roll)
|
||
|
|
self._silence_ms = 0
|
||
|
|
else:
|
||
|
|
self._voiced_ms = 0
|
||
|
|
return None
|
||
|
|
|
||
|
|
self._buffer.extend(frame)
|
||
|
|
if speech:
|
||
|
|
self._silence_ms = 0
|
||
|
|
else:
|
||
|
|
self._silence_ms += FRAME_MS
|
||
|
|
|
||
|
|
utterance_ms = len(self._buffer) * FRAME_MS // len(frame)
|
||
|
|
if self._silence_ms >= self.config.end_ms or utterance_ms >= self.config.max_utterance_ms:
|
||
|
|
utterance = bytes(self._buffer)
|
||
|
|
self.reset()
|
||
|
|
return utterance
|
||
|
|
return None
|
||
|
|
|
||
|
|
def reset(self) -> None:
|
||
|
|
self._in_utterance = False
|
||
|
|
self._voiced_ms = 0
|
||
|
|
self._silence_ms = 0
|
||
|
|
self._buffer = bytearray()
|
||
|
|
self._pre_roll = bytearray()
|