Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations

• URL: http://arxiv.org/abs/2606.06740v1
• Date: Thu, 04 Jun 2026 21:54:56 GMT
• Title: Multilingual Multi-Speaker Unit Vocoders: A Systematic Analysis of Discrete Speech Representations
• Abstract summary: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information.<n>We analyze a BigVGAN based unit vocoder, across four Indian languages.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Discrete speech units obtained via k-means clustering of self supervised embeddings entangle phonetic, speaker, and language information, causing speaker mixing and cross-lingual interference in multilingual multi-speaker speech generation. Despite growing use in Audio LLMs and speech to speech systems, unit vocoders remain underexplored. We analyze a BigVGAN based unit vocoder, across four Indian languages. We study the interaction between cluster size and conditioning strategies using WER, speaker similarity, and unit level metrics. Results show that cluster size governs intelligibility by improving phonetic discriminability, while explicit speaker conditioning is indispensable for preventing identity collapse. Language supervision yields further gains mainly at lower cluster sizes where units remain ambiguous. Our analysis shows similar phonemes across languages collapse to the same cluster IDs at smaller inventories, with larger clusters progressively separating them.

Related papers

• L-Proto: Language-Aware Episodic Prototypical Training for Multilingual Speaker Verification [49.128847336227636]
  We propose L-Proto, a language-aware episodic training strategy that constructs language-consistent episodes.<n> Experiments on the TidyVoice Challenge benchmark demonstrate consistent performance improvements over conventional fine-tuning and random episodic sampling.
  arXiv  Detail & Related papers  (2026-06-16T01:57:41Z)
• Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics [99.89493037369071]
  Conversational automatic speech recognition remains challenging due to overlapping speech, far-field noise, and varying speaker counts.<n>Recent LLM-based systems perform well on single-speaker benchmarks, but their robustness in multi-speaker settings is unclear.<n>We systematically compare LLM-based and modular approaches along four axes: overlap, semantic fidelity, speaker count, and single- versus multi-channel input.
  arXiv  Detail & Related papers  (2026-03-24T02:01:21Z)
• Whisper Speaker Identification: Leveraging Pre-Trained Multilingual Transformers for Robust Speaker Embeddings [0.0]
  We propose WSI (Whisper Speaker Identification), a framework that repurposes the Whisper automatic speech recognition model pre trained on extensive multilingual data.<n>By capitalizing on Whisper language-agnostic acoustic representations, our approach effectively distinguishes speakers across diverse languages.
  arXiv  Detail & Related papers  (2025-03-13T15:11:28Z)
• Self-Supervised Syllable Discovery Based on Speaker-Disentangled HuBERT [10.18337180909434]
  Self-supervised speech representation learning has become essential for extracting meaningful features from untranscribed audio. We propose a speech-only self-supervised fine-tuning approach that separates syllabic units from speaker information.
  arXiv  Detail & Related papers  (2024-09-16T09:07:08Z)
• DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding [51.32965203977845]
  We propose the use of discrete speech units (DSU) instead of continuous-valued speech encoder outputs. The proposed model shows robust performance on speech inputs from seen/unseen domains and instruction-following capability in spoken question answering. Our findings suggest that the ASR task and datasets are not crucial in instruction-tuning for spoken question answering tasks.
  arXiv  Detail & Related papers  (2024-06-13T17:28:13Z)
• Multilingual self-supervised speech representations improve the speech recognition of low-resource African languages with codeswitching [65.74653592668743]
  Finetuning self-supervised multilingual representations reduces absolute word error rates by up to 20%. In circumstances with limited training data finetuning self-supervised representations is a better performing and viable solution.
  arXiv  Detail & Related papers  (2023-11-25T17:05:21Z)
• Improving Speaker Diarization using Semantic Information: Joint Pairwise Constraints Propagation [53.01238689626378]
  We propose a novel approach to leverage semantic information in speaker diarization systems. We introduce spoken language understanding modules to extract speaker-related semantic information. We present a novel framework to integrate these constraints into the speaker diarization pipeline.
  arXiv  Detail & Related papers  (2023-09-19T09:13:30Z)
• ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech [58.93395189153713]
  We extend the pretraining method for cross-lingual multi-speaker speech synthesis tasks. We propose a speech-text joint pretraining framework, where we randomly mask the spectrogram and the phonemes. Our model shows great improvements over speaker-embedding-based multi-speaker TTS methods.
  arXiv  Detail & Related papers  (2022-11-07T13:35:16Z)
• LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers [71.76680102779765]
  Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. We propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers.
  arXiv  Detail & Related papers  (2022-11-05T04:03:55Z)
• Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation [31.87235700253597]
  This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units.
  arXiv  Detail & Related papers  (2021-04-02T11:43:07Z)
• U-vectors: Generating clusterable speaker embedding from unlabeled data [0.0]
  This paper introduces a speaker recognition strategy dealing with unlabeled data. It generates clusterable embedding vectors from small fixed-size speech frames. We conclude that the proposed approach achieves remarkable performance using pairwise architectures.
  arXiv  Detail & Related papers  (2021-02-07T18:00:09Z)
• Unsupervised Pattern Discovery from Thematic Speech Archives Based on Multilingual Bottleneck Features [41.951988293049205]
  We propose a two-stage approach, which comprises unsupervised acoustic modeling and decoding, followed by pattern mining in acoustic unit sequences. The proposed system is able to effectively extract topic-related words and phrases from the lecture recordings on MIT OpenCourseWare.
  arXiv  Detail & Related papers  (2020-11-03T20:06:48Z)

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.