English
Related papers

Related papers: Letter to Sound Rules for Accented Lexicon Compres…

200 papers

Deep learning technology has been widely applied to speech enhancement. While testing the effectiveness of various network structures, researchers are also exploring the improvement of the loss function used in network training. Although…

Audio and Speech Processing · Electrical Eng. & Systems 2023-04-25 Tianrui Wang , Weibin Zhu

Despite their success in speech processing, neural networks often operate as black boxes, prompting the question: what informs their decisions, and how can we interpret them? This work examines this issue in the context of lexical stress. A…

Computation and Language · Computer Science 2026-02-13 Itai Allouche , Itay Asael , Rotem Rousso , Vered Dassa , Ann Bradlow , Seung-Eun Kim , Matthew Goldrick , Joseph Keshet

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

Computation and Language · Computer Science 2017-06-13 Xiaohui Zhang , Vimal Manohar , Daniel Povey , Sanjeev Khudanpur

In expressive speech synthesis it is widely adopted to use latent prosody representations to deal with variability of the data during training. Same text may correspond to various acoustic realizations, which is known as a one-to-many…

Audio and Speech Processing · Electrical Eng. & Systems 2023-02-13 Mikolaj Babianski , Kamil Pokora , Raahil Shah , Rafal Sienkiewicz , Daniel Korzekwa , Viacheslav Klimkov

Accented automatic speech recognition (ASR) often degrades due to the limited availability of accented training data. Prior work has explored accent modeling in low-resource settings, but existing approaches typically require minutes to…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

Computation and Language · Computer Science 2024-10-31 Maxime Poli , Emmanuel Chemla , Emmanuel Dupoux

Text-to-speech (TTS) synthesis is the process of producing synthesized speech from text or phoneme input. Traditional TTS models contain multiple processing steps and require external aligners, which provide attention alignments of…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-08 Hyunseung Chung , Sang-Hoon Lee , Seong-Whan Lee

This paper presents a tree-to-tree transduction method for sentence compression. Our model is based on synchronous tree substitution grammar, a formalism that allows local distortion of the tree topology and can thus naturally capture…

Computation and Language · Computer Science 2014-01-23 Trevor Anthony Cohn , Mirella Lapata

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

Audio and Speech Processing · Electrical Eng. & Systems 2019-07-26 Loren Lugosch , Mirco Ravanelli , Patrick Ignoto , Vikrant Singh Tomar , Yoshua Bengio

Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…

Computation and Language · Computer Science 2026-05-14 Chong Li , Yingzhuo Deng , Wen Yang , Jiajun Zhang , Chengqing Zong

Lyrics alignment in long music recordings can be memory exhaustive when performed in a single pass. In this study, we present a novel method that performs audio-to-lyrics alignment with a low memory consumption footprint regardless of the…

Sound · Computer Science 2021-02-19 Emir Demirel , Sven Ahlbäck , Simon Dixon

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby coupling the model to that compressor. This work introduces…

Computation and Language · Computer Science 2026-05-15 Lin Zheng , Xinyu Li , Qian Liu , Xiachong Feng , Lingpeng Kong

Prompt compression methods enhance the efficiency of Large Language Models (LLMs) and minimize the cost by reducing the length of input context. The goal of prompt compression is to shorten the LLM prompt while maintaining a high generation…

Computation and Language · Computer Science 2025-08-25 Tinghui Zhang , Yifan Wang , Daisy Zhe Wang

We propose spoken sentence embeddings which capture both acoustic and linguistic content. While existing works operate at the character, phoneme, or word level, our method learns long-term dependencies by modeling speech at the sentence…

Sound · Computer Science 2019-02-22 Albert Haque , Michelle Guo , Prateek Verma , Li Fei-Fei

Despite it being the cornerstone of BPE, the most common tokenization algorithm, the importance of compression in the tokenization process is still unclear. In this paper, we argue for the theoretical importance of compression, that can be…

Computation and Language · Computer Science 2024-06-25 Omer Goldman , Avi Caciularu , Matan Eyal , Kris Cao , Idan Szpektor , Reut Tsarfaty

In this work, we introduce a framework for speech summarization that leverages the processing and reasoning capabilities of large language models (LLMs). We propose an end-to-end system that combines an instruction-tuned LLM with an audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-16 Wonjune Kang , Deb Roy

Phonetic information and linguistic knowledge are an essential component of a Text-to-speech (TTS) front-end. Given a language, a lexicon can be collected offline and Grapheme-to-Phoneme (G2P) relationships are usually modeled in order to…

Computation and Language · Computer Science 2023-08-01 Giulia Comini , Manuel Sam Ribeiro , Fan Yang , Heereen Shim , Jaime Lorenzo-Trueba

We study speech language models that incorporate semantic initialization and planning losses to achieve robust and consistent generation. Our approach initializes speech tokens with self-supervised features, applies a light alignment loss,…

Computation and Language · Computer Science 2025-10-01 Morteza Rohanian , Michael Krauthammer

In Linguistics, a grapheme is a written unit of a writing system corresponding to a phonological sound. In Natural Language Processing tasks, written language is analysed through two different mediums, word analysis, and character analysis.…

Computation and Language · Computer Science 2024-04-03 Samuel Rose , Chandrasekhar Kambhampati

Code-Switching refers to the phenomenon of switching languages within a sentence or discourse. However, limited code-switching , different language phoneme-sets and high rebuilding costs throw a challenge to make the specialized acoustic…

Sound · Computer Science 2022-10-27 Wei Wang , Chao Zhang , Xiaopei Wu