Description #

Audio silence detection processor that intelligently identifies whether audio is completely silent

Key features #

• Silence detection: Analyzes the entire audio file to determine whether it is silent
• Configurable threshold: Supports custom sensitivity threshold (dB) for silence detection
• Efficient processing: Optimized volume analysis algorithm for fast processing speed
• Accurate analysis: Determines silence status using professional volume detection technology
• Supports local files, HTTP/HTTPS URLs, and TOS/S3 storage

Format support #

• Input: Mainstream audio formats such as MP3, WAV, FLAC, AAC, M4A, and OGG
• Detection algorithm: Based on professional volume analysis technology
• Sampling rate: Automatically adapts to various sampling rates
• Channels: Supports mono and multi-channel audio

Detection principle #

• Volume threshold detection: Analyzes the maximum and average volume of the audio
• Silence determination: When the maximum volume is lower than the set threshold, the audio is considered silent
• Lossless analysis: Uses professional audio processing technology to ensure analysis accuracy

Operator parameters #

Input #

Output #

A Boolean column storing the results of silence detection: True indicates silence, False indicates non-silence, and None indicates processing failure or no channel

Parameters #

If a parameter does not have a default value, it is required

Examples #

The following code demonstrates how to use Daft (for distributed environments) to run the operator for audio silence detection.

from __future__ import annotations

import os

import daft
from daft import col
from daft.las.functions.audio import AudioSilenceDetection
from daft.las.functions.udf import las_udf

if __name__ == "__main__":
    TOS_TEST_DIR_URL = os.getenv("TOS_TEST_DIR_URL", "las-cn-beijing-public-online.tos-cn-beijing.volces.com")

    if os.getenv("DAFT_RUNNER", "native") == "ray":
        import logging

        import ray

        def configure_logging():
            logging.basicConfig(
                level=logging.INFO,
                format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
                datefmt="%Y-%m-%d %H:%M:%S",
            )
            logging.getLogger("tracing.span").setLevel(logging.WARNING)
            logging.getLogger("daft_io.stats").setLevel(logging.WARNING)
            logging.getLogger("DaftStatisticsManager").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaScheduler").setLevel(logging.WARNING)
            logging.getLogger("DaftFlotillaDispatcher").setLevel(logging.WARNING)

        ray.init(dashboard_host="0.0.0.0", runtime_env={"worker_process_setup_hook": configure_logging})
        daft.set_runner_ray()

    daft.set_execution_config(actor_udf_ready_timeout=600)
    daft.set_execution_config(min_cpu_per_task=0)

    samples = {
        "input_path": [
            f"https://{TOS_TEST_DIR_URL}/public/archive/audio_silence_detection/sample_silence.wav",
            f"https://{TOS_TEST_DIR_URL}/public/archive/audio_silence_detection/sample_speech.wav",
        ],
    }
    ds = daft.from_pydict(samples)

    # Using Daft to detect silence in audio files
    constructor_kwargs = {
        "silence_threshold_db": -60.0,
        "timeout": 30,
    }

    ds = ds.with_column(
        "is_silence",
        las_udf(
            AudioSilenceDetection,
            construct_args=constructor_kwargs,
            num_cpus=1,
            concurrency=1,
            batch_size=1,
        )(col("input_path")),
    )

    ds.show()
    # ╭────────────────────────────────┬────────────╮
    # │ input_path                     ┆ is_silence │
    # │ ---                            ┆ ---        │
    # │ String                         ┆ Bool       │
    # ╞════════════════════════════════╪════════════╡
    # │ https://las-public-data-qa.to… ┆ true       │
    # ├╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌╌╌┤
    # │ https://las-public-data-qa.to… ┆ false      │
    # ╰────────────────────────────────┴────────────╯