End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations

• URL: http://arxiv.org/abs/2303.12002v3
• Date: Wed, 22 May 2024 07:42:01 GMT
• Title: End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations
• Authors: Giovanni Morrone, Samuele Cornell, Luca Serafini, Enrico Zovato, Alessio Brutti, Stefano Squartini,
• Abstract summary: Speech separation guided diarization (SSGD) performs diarization by first separating the speakers and then applying voice activity detection (VAD) on each separated stream. We consider three state-of-the-art speech separation (SSep) algorithms and study their performance in online and offline scenarios. We show that our best model achieves 8.8% DER on CALLHOME, which outperforms the current state-of-the-art end-to-end neural diarization model.
• Score: 13.020158123538138
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Recent works show that speech separation guided diarization (SSGD) is an increasingly promising direction, mainly thanks to the recent progress in speech separation. It performs diarization by first separating the speakers and then applying voice activity detection (VAD) on each separated stream. In this work we conduct an in-depth study of SSGD in the conversational telephone speech (CTS) domain, focusing mainly on low-latency streaming diarization applications. We consider three state-of-the-art speech separation (SSep) algorithms and study their performance both in online and offline scenarios, considering non-causal and causal implementations as well as continuous SSep (CSS) windowed inference. We compare different SSGD algorithms on two widely used CTS datasets: CALLHOME and Fisher Corpus (Part 1 and 2) and evaluate both separation and diarization performance. To improve performance, a novel, causal and computationally efficient leakage removal algorithm is proposed, which significantly decreases false alarms. We also explore, for the first time, fully end-to-end SSGD integration between SSep and VAD modules. Crucially, this enables fine-tuning on real-world data for which oracle speakers sources are not available. In particular, our best model achieves 8.8% DER on CALLHOME, which outperforms the current state-of-the-art end-to-end neural diarization model, despite being trained on an order of magnitude less data and having significantly lower latency, i.e., 0.1 vs. 1 s. Finally, we also show that the separated signals can be readily used also for automatic speech recognition, reaching performance close to using oracle sources in some configurations.

Related papers

• DMDSpeech: Distilled Diffusion Model Surpassing The Teacher in Zero-shot Speech Synthesis via Direct Metric Optimization [12.310318928818546]
  We propose a novel method of distilling TTS diffusion models with direct end-to-end evaluation metric optimization. We show DMDSpeech consistently surpasses prior state-of-the-art models in both naturalness and speaker similarity. This work highlights the potential of direct metric optimization in speech synthesis, allowing models to better align with human auditory preferences.
  arXiv  Detail & Related papers  (2024-10-14T21:17:58Z)
• Online speaker diarization of meetings guided by speech separation [0.0]
  Overlapped speech is notoriously problematic for speaker diarization systems. We introduce a new speech separation-guided diarization scheme suitable for the online speaker diarization of long meeting recordings.
  arXiv  Detail & Related papers  (2024-01-30T09:09:22Z)
• Audio-Visual Efficient Conformer for Robust Speech Recognition [91.3755431537592]
  We propose to improve the noise of the recently proposed Efficient Conformer Connectionist Temporal Classification architecture by processing both audio and visual modalities. Our experiments show that using audio and visual modalities allows to better recognize speech in the presence of environmental noise and significantly accelerate training, reaching lower WER with 4 times less training steps.
  arXiv  Detail & Related papers  (2023-01-04T05:36:56Z)
• Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network [58.82343017711883]
  This paper investigates how to learn directly from unpaired phone sequences and speech utterances. GAN training is adopted in the first stage to find the mapping relationship between unpaired speech and phone sequence. In the second stage, another HMM model is introduced to train from the generator's output, which boosts the performance.
  arXiv  Detail & Related papers  (2022-07-29T09:29:28Z)
• Learning Long-Term Spatial-Temporal Graphs for Active Speaker Detection [21.512786675773675]
  Active speaker detection in videos with multiple speakers is a challenging task. We present SPELL, a novel spatial-temporal graph learning framework. SPELL is able to reason over long temporal contexts for all nodes without relying on computationally expensive fully connected graph neural networks.
  arXiv  Detail & Related papers  (2022-07-15T23:43:17Z)
• STOP: A dataset for Spoken Task Oriented Semantic Parsing [66.14615249745448]
  End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. We release the Spoken Task-Oriented semantic Parsing (STOP) dataset, the largest and most complex SLU dataset to be publicly available. In addition to the human-recorded audio, we are releasing a TTS-generated version to benchmark the performance for low-resource domain adaptation of end-to-end SLU systems.
  arXiv  Detail & Related papers  (2022-06-29T00:36:34Z)
• Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation [76.13334392868208]
  Direct speech-to-speech translation (S2ST) models suffer from data scarcity issues. In this work, we explore self-supervised pre-training with unlabeled speech data and data augmentation to tackle this issue.
  arXiv  Detail & Related papers  (2022-04-06T17:59:22Z)
• End-to-End Active Speaker Detection [58.7097258722291]
  We propose an end-to-end training network where feature learning and contextual predictions are jointly learned. We also introduce intertemporal graph neural network (iGNN) blocks, which split the message passing according to the main sources of context in the ASD problem. Experiments show that the aggregated features from the iGNN blocks are more suitable for ASD, resulting in state-of-the art performance.
  arXiv  Detail & Related papers  (2022-03-27T08:55:28Z)
• Target-Speaker Voice Activity Detection: a Novel Approach for Multi-Speaker Diarization in a Dinner Party Scenario [51.50631198081903]
  We propose a novel Target-Speaker Voice Activity Detection (TS-VAD) approach. TS-VAD directly predicts an activity of each speaker on each time frame. Experiments on the CHiME-6 unsegmented data show that TS-VAD achieves state-of-the-art results.
  arXiv  Detail & Related papers  (2020-05-14T21:24:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.