中文
相关论文

相关论文: Preserving Phonemic Distinctions for Ordinal Regre…

200 篇论文

Acoustic-to-articulatory speech inversion could enhance automated clinical mispronunciation detection to provide detailed articulatory feedback unattainable by formant-based mispronunciation detection algorithms; however, it is unclear the…

音频与语音处理 · 电气工程与系统科学 2023-08-22 Nina R Benway , Yashish M Siriwardena , Jonathan L Preston , Elaine Hitchcock , Tara McAllister , Carol Espy-Wilson

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

音频与语音处理 · 电气工程与系统科学 2022-09-19 David M. Chan , Shalini Ghosh , Debmalya Chakrabarty , Björn Hoffmeister

The fundamental frequency (F0) contour of speech is a key aspect to represent speech prosody that finds use in speech and spoken language analysis such as voice conversion and speech synthesis as well as speaker and language identification.…

音频与语音处理 · 电气工程与系统科学 2018-05-09 Akihiro Kato , Tomi Kinnunen

User-defined keyword spotting (KWS) enhances the user experience by allowing individuals to customize keywords. However, in open-vocabulary scenarios, most existing methods commonly suffer from high false alarm rates with confusable words…

音频与语音处理 · 电气工程与系统科学 2024-12-31 Li Kewei , Zhou Hengshun , Shen Kai , Dai Yusheng , Du Jun

Neural language models are usually trained to match the distributional properties of a large-scale corpus by minimizing the log loss. While straightforward to optimize, this approach forces the model to reproduce all variations in the…

计算与语言 · 计算机科学 2020-05-04 Daniel Kang , Tatsunori Hashimoto

Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is…

音频与语音处理 · 电气工程与系统科学 2020-08-12 Umut Isik , Ritwik Giri , Neerad Phansalkar , Jean-Marc Valin , Karim Helwani , Arvindh Krishnaswamy

Neuromorphic computing, inspired by nervous systems, revolutionizes information processing with its focus on efficiency and low power consumption. Using sparse coding, this paradigm enhances processing efficiency, which is crucial for edge…

声音 · 计算机科学 2025-09-01 Soufiyan Bahadi , Eric Plourde , Jean Rouat

Process reward models (PRMs) offer fine-grained, step-level evaluations that facilitate deeper reasoning processes in large language models (LLMs), proving effective in complex tasks like mathematical reasoning. However, developing PRMs is…

机器学习 · 计算机科学 2025-10-15 Yuyang Ding , Xinyu Shi , Juntao Li , Xiaobo Liang , Zhaopeng Tu , Min Zhang

Many applications of speech technology require more and more audio data. Automatic assessment of the quality of the collected recordings is important to ensure they meet the requirements of the related applications. However, effective and…

音频与语音处理 · 电气工程与系统科学 2020-05-19 Qiang Huang , Thomas Hain

Traditional audiometry often fails to fully characterize the functional impact of hearing loss on speech understanding, particularly supra-threshold deficits and frequency-specific perception challenges in conditions like presbycusis. This…

声音 · 计算机科学 2025-05-29 Stefan Bleeck

Parkinson's Disease (PD) affects over 10 million people worldwide, with speech impairments in up to 89% of patients. Current speech-based detection systems analyze entire utterances, potentially overlooking the diagnostic value of specific…

计算与语言 · 计算机科学 2025-10-07 Ilias Tougui , Mehdi Zakroum , Mounir Ghogho

Multilingual models can improve language processing, particularly for low resource situations, by sharing parameters across languages. Multilingual acoustic models, however, generally ignore the difference between phonemes (sounds that can…

Recent work uses reinforcement learning (RL) to fine-tune text-to-image diffusion models, improving text-image alignment and sample quality. However, existing approaches introduce unnecessary complexity: they cache the full sampling…

机器学习 · 计算机科学 2025-07-02 Yanting Miao , William Loh , Pacal Poupart , Suraj Kothawade

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…

Recent advances in machine learning and the availability of articulatory datasets allow vocal tract synthesis to be conditioned on phonetic sequences, a primary task of articulatory speech synthesis. However, quality assessment needs a…

计算与语言 · 计算机科学 2026-05-21 Vinicius Ribeiro , Yves Laprie

In recent research, in the domain of speech processing, large End-to-End (E2E) systems for Automatic Speech Recognition (ASR) have reported state-of-the-art performance on various benchmarks. These systems intrinsically learn how to handle…

计算与语言 · 计算机科学 2023-09-06 Patrick Eickhoff , Matthias Möller , Theresa Pekarek Rosin , Johannes Twiefel , Stefan Wermter

Recent models for unsupervised representation learning of text have employed a number of techniques to improve contextual word representations but have put little focus on discourse-level representations. We propose CONPONO, an…

计算与语言 · 计算机科学 2020-05-22 Dan Iter , Kelvin Guu , Larry Lansing , Dan Jurafsky

The relationship between written and spoken words is convoluted in languages with a deep orthography such as English and therefore it is difficult to devise explicit rules for generating the pronunciations for unseen words. Pronunciation by…

计算与语言 · 计算机科学 2011-09-22 Janne V. Kujala , Aleksi Keurulainen

Local dialects influence people to pronounce words of the same language differently from each other. The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic…

音频与语音处理 · 电气工程与系统科学 2020-03-05 Genta Indra Winata , Samuel Cahyawijaya , Zihan Liu , Zhaojiang Lin , Andrea Madotto , Peng Xu , Pascale Fung

The goal of this work is to recover articulatory information from the speech signal by acoustic-to-articulatory inversion. One of the main difficulties with inversion is that the problem is underdetermined and inversion methods generally…

计算与语言 · 计算机科学 2007-05-23 Blaise Potard , Yves Laprie
‹ 上一页 1 8 9 10 下一页 ›