English
Related papers

Related papers: Analyzing and Mitigating Inconsistency in Discrete…

200 papers

Dense Retrieval (DR) reaches state-of-the-art results in first-stage retrieval, but little is known about the mechanisms that contribute to its success. Therefore, in this work, we conduct an interpretation study of recently proposed DR…

Information Retrieval · Computer Science 2021-11-30 Jingtao Zhan , Jiaxin Mao , Yiqun Liu , Jiafeng Guo , Min Zhang , Shaoping Ma

Most of the prevalent approaches in speech prosody modeling rely on learning global style representations in a continuous latent space which encode and transfer the attributes of reference speech. However, recent work on neural codecs which…

Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation improves encoded representations, it does not guarantee content preservation in reconstructed…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-09 Junhyeok Lee , Xiluo He , Jihwan Lee , Helin Wang , Shrikanth Narayanan , Thomas Thebaud , Laureano Moro-Velazquez , Jesús Villalba , Najim Dehak

Audio generation has long been fragmented, with speech, music, and sound effects produced by domain-specific models that fail to jointly generate coherent audio scenes from a single description. The key obstacles are insufficient…

Ever since the successful application of sequence to sequence learning for neural machine translation systems, interest has surged in its applicability towards language generation in other problem domains. Recent work has investigated the…

Computation and Language · Computer Science 2017-10-31 Sharath T. S. , Shubhangi Tandon , Ryan Bauer

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…

Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucination detection methods often perform poorly on sentence-level…

Computation and Language · Computer Science 2025-09-01 Weizhi Gao , Xiaorui Liu , Feiyi Wang , Dan Lu , Junqi Yin

In this paper, we propose a personalized neural speech codec, envisioning that personalization can reduce the model complexity or improve perceptual speech quality. Despite the common usage of speech codecs where only a single talker is…

Sound · Computer Science 2024-04-02 Inseon Jang , Haici Yang , Wootaek Lim , Seungkwon Beack , Minje Kim

Continuous speech can be converted into a discrete sequence by deriving discrete units from the hidden features of self-supervised learned (SSL) speech models. Although SSL models are becoming larger and trained on more data, they are often…

Audio and Speech Processing · Electrical Eng. & Systems 2025-02-06 Jakob Poncelet , Yujun Wang , Hugo Van hamme

Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and imaging devices. Existing approaches often reduce this diversity to consensus labels or…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Sanaz Karimijafarbigloo , Armin Khosravi , Alireza Kheyrkhah , Reza Azad , Mauricio Reyes , Dorit Merhof

Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…

Sound · Computer Science 2024-01-24 Huaying Xue , Xiulian Peng , Yan Lu

Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech codecs employ either acoustic features or learned blind…

Sound · Computer Science 2025-10-16 Xue Jiang , Xiulian Peng , Huaying Xue , Yuan Zhang , Yan Lu

Self-supervised learning (SSL) proficiency in speech-related tasks has driven research into utilizing discrete tokens for speech tasks like recognition and translation, which offer lower storage requirements and great potential to employ…

Audio and Speech Processing · Electrical Eng. & Systems 2023-12-15 Yifan Yang , Feiyu Shen , Chenpeng Du , Ziyang Ma , Kai Yu , Daniel Povey , Xie Chen

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

Sound · Computer Science 2025-07-18 Luca Della Libera , Cem Subakan , Mirco Ravanelli

Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference…

Sound · Computer Science 2026-04-14 Junchuan Zhao , Minh Duc Vu , Ye Wang

The pursuit of a "unified" discrete token for both speech understanding and generation has led the Speech Language Model (SLM) community to heavily rely on Word Error Rate (WER) -- the core metric for Whisper-style tokenizers -- as the…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-29 Xiangyu Zhang , Yuxin Li , Haoyang Zhang , Shiqi Han , Hexin Liu , Qiquan Zhang , Beena Ahmed , Julien Epps

Large Language Models (LLMs), despite their impressive capabilities, often fail to accurately repeat a single word when prompted to, and instead output unrelated text. This unexplained failure mode represents a vulnerability, allowing even…

Machine Learning · Computer Science 2025-03-13 Itay Yona , Ilia Shumailov , Jamie Hayes , Federico Barbero , Yossi Gandelsman

Multi-speaker speech recognition of unsegmented recordings has diverse applications such as meeting transcription and automatic subtitle generation. With technical advances in systems dealing with speech separation, speaker diarization, and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-05 Desh Raj , Pavel Denisov , Zhuo Chen , Hakan Erdogan , Zili Huang , Maokui He , Shinji Watanabe , Jun Du , Takuya Yoshioka , Yi Luo , Naoyuki Kanda , Jinyu Li , Scott Wisdom , John R. Hershey

Sequential Recommenders generate recommendations based on users' historical interaction sequences. However, in practice, these collected sequences are often contaminated by noisy interactions, which significantly impairs recommendation…

Information Retrieval · Computer Science 2025-06-10 Bohao Wang , Feng Liu , Changwang Zhang , Jiawei Chen , Yudi Wu , Sheng Zhou , Xingyu Lou , Jun Wang , Yan Feng , Chun Chen , Can Wang

This study presents a comparative analysis of the statistical and linguistic properties of neural audio codecs (NACs). We investigate discrete speech tokens produced by various NAC models, examining their adherence to linguistic statistical…

Computation and Language · Computer Science 2025-09-03 Joonyong Park , Shinnosuke Takamichi , David M. Chan , Shunsuke Kando , Yuki Saito , Hiroshi Saruwatari