Sortformer: Seamless Integration of Speaker Diarization and ASR by Bridging Timestamps and Tokens
- URL: http://arxiv.org/abs/2409.06656v1
- Date: Tue, 10 Sep 2024 17:20:11 GMT
- Title: Sortformer: Seamless Integration of Speaker Diarization and ASR by Bridging Timestamps and Tokens
- Authors: Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, He Huang, Nithin Rao Koluguri, Krishna C. Puvvada, Jagadeesh Balam, Boris Ginsburg,
- Abstract summary: We propose Sortformer, a novel neural model for speaker diarization.
We introduce Sort Loss, which enables a diarization model to autonomously resolve permutation, with or without PIL.
Code and trained models will be made publicly available via the NVIDIA NeMo framework.
- Score: 27.08293218877395
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We propose Sortformer, a novel neural model for speaker diarization, trained with unconventional objectives compared to existing end-to-end diarization models. The permutation problem in speaker diarization has long been regarded as a critical challenge. Most prior end-to-end diarization systems employ permutation invariant loss (PIL), which optimizes for the permutation that yields the lowest error. In contrast, we introduce Sort Loss, which enables a diarization model to autonomously resolve permutation, with or without PIL. We demonstrate that combining Sort Loss and PIL achieves performance competitive with state-of-the-art end-to-end diarization models trained exclusively with PIL. Crucially, we present a streamlined multispeaker ASR architecture that leverages Sortformer as a speaker supervision model, embedding speaker label estimation within the ASR encoder state using a sinusoidal kernel function. This approach resolves the speaker permutation problem through sorted objectives, effectively bridging speaker-label timestamps and speaker tokens. In our experiments, we show that the proposed multispeaker ASR architecture, enhanced with speaker supervision, improves performance via adapter techniques. Code and trained models will be made publicly available via the NVIDIA NeMo framework
Related papers
- Unispeaker: A Unified Approach for Multimodality-driven Speaker Generation [66.49076386263509]
This paper introduces UniSpeaker, a unified approach for multimodality-driven speaker generation.<n>We propose a unified voice aggregator based on KV-Former, applying soft contrastive loss to map diverse voice description modalities into a shared voice space.<n>UniSpeaker is evaluated across five tasks using the MVC benchmark, and the experimental results demonstrate that UniSpeaker outperforms previous modality-specific models.
arXiv Detail & Related papers (2025-01-11T00:47:29Z) - From Modular to End-to-End Speaker Diarization [3.079020586262228]
We describe a system based on a Bayesian hidden Markov model used to cluster x-vectors (speaker embeddings obtained with a neural network), known as VBx.
We describe an approach for generating synthetic data which resembles real conversations in terms of speaker turns and overlaps.
We show how this method generating simulated conversations'' allows for better performance than using a previously proposed method for creating simulated mixtures'' when training the popular EEND.
arXiv Detail & Related papers (2024-06-27T15:09:39Z) - Controllable speech synthesis by learning discrete phoneme-level
prosodic representations [53.926969174260705]
We present a novel method for phoneme-level prosody control of F0 and duration using intuitive discrete labels.
We propose an unsupervised prosodic clustering process which is used to discretize phoneme-level F0 and duration features from a multispeaker speech dataset.
arXiv Detail & Related papers (2022-11-29T15:43:36Z) - Human-in-the-loop Speaker Adaptation for DNN-based Multi-speaker TTS [36.023566245506046]
We propose a human-in-the-loop speaker-adaptation method for multi-speaker text-to-speech.
The proposed method uses a sequential line search algorithm that repeatedly asks a user to select a point on a line segment in the embedding space.
Experimental results indicate that the proposed method can achieve comparable performance to the conventional one in objective and subjective evaluations.
arXiv Detail & Related papers (2022-06-21T11:08:05Z) - Streaming Speaker-Attributed ASR with Token-Level Speaker Embeddings [53.11450530896623]
This paper presents a streaming speaker-attributed automatic speech recognition (SA-ASR) model that can recognize "who spoke what"
Our model is based on token-level serialized output training (t-SOT) which was recently proposed to transcribe multi-talker speech in a streaming fashion.
The proposed model achieves substantially better accuracy than a prior streaming model and shows comparable or sometimes even superior results to the state-of-the-art offline SA-ASR model.
arXiv Detail & Related papers (2022-03-30T21:42:00Z) - Speaker Embedding-aware Neural Diarization: a Novel Framework for
Overlapped Speech Diarization in the Meeting Scenario [51.5031673695118]
We reformulate overlapped speech diarization as a single-label prediction problem.
We propose the speaker embedding-aware neural diarization (SEND) system.
arXiv Detail & Related papers (2022-03-18T06:40:39Z) - Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech [62.95422526044178]
We use Model Agnostic Meta-Learning (MAML) as the training algorithm of a multi-speaker TTS model.
We show that Meta-TTS can synthesize high speaker-similarity speech from few enrollment samples with fewer adaptation steps than the speaker adaptation baseline.
arXiv Detail & Related papers (2021-11-07T09:53:31Z) - End-to-End Diarization for Variable Number of Speakers with Local-Global
Networks and Discriminative Speaker Embeddings [66.50782702086575]
We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings.
The proposed system is designed to handle meetings with unknown numbers of speakers, using variable-number permutation-invariant cross-entropy based loss functions.
arXiv Detail & Related papers (2021-05-05T14:55:29Z) - Voice Conversion Based Speaker Normalization for Acoustic Unit Discovery [3.128267020893596]
We propose an unsupervised speaker normalization technique prior to unit discovery.
It is based on separating speaker related from content induced variations in a speech signal with an adversarial contrastive predictive coding approach.
Experiments on English, Yoruba and Mboshi show improvements compared to using non-normalized input.
arXiv Detail & Related papers (2021-05-04T22:40:41Z) - Streaming end-to-end multi-talker speech recognition [34.76106500736099]
We propose the Streaming Unmixing and Recognition Transducer (SURT) for end-to-end multi-talker speech recognition.
Our model employs the Recurrent Neural Network Transducer (RNN-T) as the backbone that can meet various latency constraints.
Based on experiments on the publicly available LibriSpeechMix dataset, we show that HEAT can achieve better accuracy compared with PIT.
arXiv Detail & Related papers (2020-11-26T06:28:04Z) - Integrating end-to-end neural and clustering-based diarization: Getting
the best of both worlds [71.36164750147827]
Clustering-based approaches assign speaker labels to speech regions by clustering speaker embeddings such as x-vectors.
End-to-end neural diarization (EEND) directly predicts diarization labels using a neural network.
We propose a simple but effective hybrid diarization framework that works with overlapped speech and for long recordings containing an arbitrary number of speakers.
arXiv Detail & Related papers (2020-10-26T06:33:02Z) - Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence
Modeling [61.351967629600594]
This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach.
In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module.
Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
arXiv Detail & Related papers (2020-09-06T13:01:06Z) - Joint Speaker Counting, Speech Recognition, and Speaker Identification
for Overlapped Speech of Any Number of Speakers [38.3469744871394]
We propose an end-to-end speaker-attributed automatic speech recognition model.
It unifies speaker counting, speech recognition, and speaker identification on overlapped speech.
arXiv Detail & Related papers (2020-06-19T02:05:18Z) - NAUTILUS: a Versatile Voice Cloning System [44.700803634034486]
NAUTILUS can generate speech with a target voice either from a text input or a reference utterance of an arbitrary source speaker.
It can clone unseen voices using untranscribed speech of target speakers on the basis of the backpropagation algorithm.
It achieves comparable quality with state-of-the-art TTS and VC systems when cloning with just five minutes of untranscribed speech.
arXiv Detail & Related papers (2020-05-22T05:00:20Z) - 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) - Speaker Diarization with Lexical Information [59.983797884955]
This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition.
We propose a speaker diarization system that can incorporate word-level speaker turn probabilities with speaker embeddings into a speaker clustering process to improve the overall diarization accuracy.
arXiv Detail & Related papers (2020-04-13T17:16:56Z) - End-to-End Neural Diarization: Reformulating Speaker Diarization as
Simple Multi-label Classification [45.38809571153867]
We propose the End-to-End Neural Diarization (EEND) in which a neural network directly outputs speaker diarization results.
By feeding multi-speaker recordings with corresponding speaker segment labels, our model can be easily adapted to real conversations.
arXiv Detail & Related papers (2020-02-24T14:53:32Z)
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.