English
Related papers

Related papers: Real-time Speech Interruption Analysis: From Cloud…

200 papers

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

Sound · Computer Science 2026-03-17 Zhengyan Sheng , Zhihao Du , Shiliang Zhang , Zhijie Yan , Liping Chen

Diffusion models are a class of generative models that have been recently used for speech enhancement with remarkable success but are computationally expensive at inference time. Therefore, these models are impractical for processing…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-15 Bunlong Lay , Rostislav Makarov , Timo Gerkmann

Full-duplex spoken dialogue systems promise to transform human-machine interaction from a rigid, turn-based protocol into a fluid, natural conversation. However, the central challenge to realizing this vision, managing overlapping speech,…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-28 Guan-Ting Lin , Shih-Yun Shan Kuan , Qirui Wang , Jiachen Lian , Tingle Li , Shinji Watanabe , Hung-yi Lee

The past ten years have witnessed the rapid development of text-based intent detection, whose benchmark performances have already been taken to a remarkable level by deep learning techniques. However, automatic speech recognition (ASR)…

Computation and Language · Computer Science 2022-05-24 Peilin Zhou , Dading Chong , Helin Wang , Qingcheng Zeng

In this paper, we introduce a streaming keyphrase detection system that can be easily customized to accurately detect any phrase composed of words from a large vocabulary. The system is implemented with an end-to-end trained automatic…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-16 Rajeev Rikhye , Quan Wang , Qiao Liang , Yanzhang He , Ding Zhao , Yiteng , Huang , Arun Narayanan , Ian McGraw

Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift, a subtle, gradual shift in perceived speaker identity within a single utterance. This underexplored…

The rapid advancement of Large Language Models (LLMs) has spurred significant progress in Large Speech-Language Models (LSLMs), enhancing their capabilities in both speech understanding and generation. While existing LSLMs often concentrate…

Computation and Language · Computer Science 2025-11-03 Shoutao Guo , Shaolei Zhang , Qingkai Fang , Zhengrui Ma , Min Zhang , Yang Feng

The prevalent communication efficient federated learning (FL) frameworks usually take advantages of model gradient compression or model distillation. However, the unbalanced local data distributions (either in quantity or quality) of…

Machine Learning · Computer Science 2023-01-31 Beibei Li , Zerui Shao , Ao Liu , Peiran Wang

Real-time Automatic Speech Recognition (ASR) is a fundamental building block for many commercial applications of ML, including live captioning, dictation, meeting transcriptions, and medical scribes. Accuracy and latency are the most…

Sound · Computer Science 2025-07-16 Atila Orhon , Arda Okan , Berkin Durmus , Zach Nagengast , Eduardo Pacheco

Environmental sound recordings often contain intelligible speech, raising privacy concerns that limit analysis, sharing and reuse of data. In this paper, we introduce a method that renders speech unintelligible while preserving both the…

Sound · Computer Science 2025-07-14 Modan Tailleur , Mathieu Lagrange , Pierre Aumond , Vincent Tourre

Social media platforms such as Twitter (now X) provide rich data for analyzing public discourse, especially during crises such as the COVID-19 pandemic. However, the brevity, informality, and noise of social media short texts often hinder…

Computation and Language · Computer Science 2025-10-23 Wangjiaxuan Xin , Shuhua Yin , Shi Chen , Yaorong Ge

We present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-08 Alexandre Defossez , Gabriel Synnaeve , Yossi Adi

Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourth axis, granularity of external verbal supervision, via Verbal Process Supervision (VPS),…

Computation and Language · Computer Science 2026-04-24 Hao-Yuan Chen

Despite rapid advances in speech recognition, current models remain brittle to superficial perturbations to their inputs. Small amounts of noise can destroy the performance of an otherwise state-of-the-art model. To harden models against…

Audio and Speech Processing · Electrical Eng. & Systems 2018-07-19 Davis Liang , Zhiheng Huang , Zachary C. Lipton

Layer pruning efficiently reduces Large Language Model (LLM) computational costs but often triggers sudden performance collapse. Existing representation-based analyses struggle to explain this mechanism. We propose studying pruning through…

Computation and Language · Computer Science 2026-05-11 Boyu Shi , Chang Liu , ChuanBao Gao , Xu Yang , Xin Geng

Recent advances in Automatic Speech Recognition (ASR) have been largely fueled by massive speech corpora. However, extending coverage to diverse languages with limited resources remains a formidable challenge. This paper introduces Speech…

Computation and Language · Computer Science 2025-05-23 Tianduo Wang , Lu Xu , Wei Lu , Shanbo Cheng

Recent research in speaker verification has increasingly focused on achieving robust and reliable recognition under challenging channel conditions and noisy environments. Identifying speakers in radio communications is particularly…

Sound · Computer Science 2024-06-18 Wenhao Yang , Jianguo Wei , Wenhuan Lu , Lei Li , Xugang Lu

Federated learning (FL) leverages client-server communications to train global models on decentralized data. However, communication noise or errors can impair model accuracy. To address this problem, we propose a novel FL algorithm that…

Machine Learning · Computer Science 2025-12-15 Ehsan Lari , Reza Arablouei , Vinay Chakravarthi Gogineni , Stefan Werner

While Large Audio Language Models (LALMs) achieve strong performance on short audio, they degrade on long-form inputs. This degradation is more severe in temporal awareness tasks, where temporal alignment becomes increasingly inaccurate as…

Audio and Speech Processing · Electrical Eng. & Systems 2026-04-27 Mingchen Shao , Hang Su , Wenjie Tian , Bingshen Mu , Zhennan Lin , Lichun Fan , Zhenbo Luo , Jian Luan , Lei Xie

Multi-agent systems using large language models (LLMs) have demonstrated impressive capabilities across various domains. However, current agent communication suffers from verbose output that overload context and increase computational…

Computation and Language · Computer Science 2026-04-09 Danqing Wang , Da Yin , Ruta Desai , Lei Li , Asli Celikyilmaz , Ansong Ni