# Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation

arXiv: https://arxiv.org/abs/2210.13248 · HTML: https://mlsanity.com/paper/2210.13248/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Oct 2022.

## Built on by (most cited first, 23 of 23)

- [Natural language guidance of high-fidelity text-to-speech with synthetic annotations](https://mlsanity.com/paper/2402.01912/) (2024)
- [DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data](https://mlsanity.com/paper/2409.20007/) (2024)
- [Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation](https://mlsanity.com/paper/2407.09886/) (2024)
- [Scaling Rich Style-Prompted Text-to-Speech Datasets](https://mlsanity.com/paper/2503.04713/) (2025)
- [IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS](https://mlsanity.com/paper/2409.05356/) (2024)
- [RASMALAI: Resources for Adaptive Speech Modeling in Indian Languages with Accents and Intonations](https://mlsanity.com/paper/2505.18609/) (2025)
- [Fifteen Years of Child-Centered Long-Form Recordings: Promises, Resources, and Remaining Challenges to Validity](https://mlsanity.com/paper/2506.11075/) (2025)
- [AnCoGen: Analysis, Control and Generation of Speech with a Masked Autoencoder](https://mlsanity.com/paper/2501.05332/) (2025)
- [Challenges in Automated Processing of Speech from Child Wearables: The Case of Voice Type Classifier](https://mlsanity.com/paper/2506.11074/) (2025)
- [Audio-Maestro: Enhancing Large Audio-Language Models with Tool-Augmented Reasoning](https://mlsanity.com/paper/2510.11454/) (2025)
- [Big model only for hard audios: Sample dependent Whisper model selection for efficient inferences](https://mlsanity.com/paper/2309.12712/) (2023)
- [ELAICHI: Enhancing Low-resource TTS by Addressing Infrequent and Low-frequency Character Bigrams](https://mlsanity.com/paper/2410.17901/) (2024)
- [Recent Trends in Distant Conversational Speech Recognition: A Review of CHiME-7 and 8 DASR Challenges](https://mlsanity.com/paper/2507.18161/) (2025)
- [CAAD: Contrastive Audio-Aware Distillation for Efficient Speech Language Models](https://mlsanity.com/paper/2606.23052/) (2026)
- [XLS-R fine-tuning on noisy word boundaries for unsupervised speech segmentation into words](https://mlsanity.com/paper/2310.05235/) (2023)
- [Investigating Affect Mining Techniques for Annotation Sample Selection in the Creation of Finnish Affective Speech Corpus](https://mlsanity.com/paper/2505.17833/) (2025)
- [Revival with Voice: Multi-modal Controllable Text-to-Speech Synthesis](https://mlsanity.com/paper/2505.18972/) (2025)
- [Analysing the Impact of Audio Quality on the Use of Naturalistic Long-Form Recordings for Infant-Directed Speech Research](https://mlsanity.com/paper/2305.01965/) (2023)
- [Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge](https://mlsanity.com/paper/2402.01413/) (2024)
- [Enabling automatic transcription of child-centered audio recordings from real-world environments](https://mlsanity.com/paper/2506.11747/) (2025)
- [Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data](https://mlsanity.com/paper/2606.13507/) (2026)
- [A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models](https://mlsanity.com/paper/2610.06057/) (2026)
- [ELARSpeech: A 30K-Hour Dataset Across 675 Underrepresented Languages for Long-Tail Multilingual Speech Technologies](https://mlsanity.com/paper/2610.19388/) (2026)

## Abstract (arXiv)

Most automatic speech processing systems register degraded performance when applied to noisy or reverberant speech. But how can one tell whether speech is noisy or reverberant? We propose Brouhaha, a neural network jointly trained to extract speech/non-speech segments, speech-to-noise ratios, and C50room acoustics from single-channel recordings. Brouhaha is trained using a data-driven approach in which noisy and reverberant audio segments are synthesized. We first evaluate its performance and demonstrate that the proposed multi-task regime is beneficial. We then present two scenarios illustrating how Brouhaha can be used on naturally noisy and reverberant data: 1) to investigate the errors made by a speaker diarization model (pyannote.audio); and 2) to assess the reliability of an automatic speech recognition model (Whisper from OpenAI). Both our pipeline and a pretrained model are open source and shared with the speech community.