English
Related papers

Related papers: Generative Spoken Language Modeling from Raw Audio

200 papers

Speech pre-training has primarily demonstrated efficacy on classification tasks, while its capability of generating novel speech, similar to how GPT-2 can generate coherent paragraphs, has barely been explored. Generative Spoken Language…

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ student/teacher training on unlabeled data, helping scale out target…

Machine Learning · Computer Science 2019-04-04 Sree Hari Krishnan Parthasarathi , Nikko Strom

Acoustic-to-Word recognition provides a straightforward solution to end-to-end speech recognition without needing external decoding, language model re-scoring or lexicon. While character-based models offer a natural solution to the…

Audio and Speech Processing · Electrical Eng. & Systems 2018-08-22 Shruti Palaskar , Florian Metze

Rapid growth in speech data demands adaptive models, as traditional static methods fail to keep pace with dynamic and diverse speech information. We introduce continuous speech learning, a new set-up targeting at bridging the adaptation gap…

Computation and Language · Computer Science 2025-06-04 Guitao Wang , Jinming Zhao , Hao Yang , Guilin Qi , Tongtong Wu , Gholamreza Haffari

In this paper, we introduce a new and simple method for comparing speech utterances without relying on text transcripts. Our speech-to-speech comparison metric utilizes state-of-the-art speech2unit encoders like HuBERT to convert speech…

Computation and Language · Computer Science 2023-07-21 Laurent Besacier , Swen Ribeiro , Olivier Galibert , Ioan Calapodescu

While several self-supervised approaches for learning discrete speech representation have been proposed, it is unclear how these seemingly similar approaches relate to each other. In this paper, we consider a generative model with discrete…

Computation and Language · Computer Science 2022-11-01 Sung-Lin Yeh , Hao Tang

Recent advancements in speech-based topic segmentation have highlighted the potential of pretrained speech encoders to capture semantic representations directly from speech. Traditionally, topic segmentation has relied on a pipeline…

Computation and Language · Computer Science 2024-09-11 Sakshi Deo Shukla , Pavel Denisov , Tugtekin Turan

A lot of work has been done to build text-based language models for performing different NLP tasks, but not much research has been done in the case of audio-based language models. This paper proposes a Convolutional Autoencoder based neural…

Computation and Language · Computer Science 2020-09-30 Prakamya Mishra , Pranav Mathur

While human evaluation is the most reliable metric for evaluating speech generation systems, it is generally costly and time-consuming. Previous studies on automatic speech quality assessment address the problem by predicting human…

Audio and Speech Processing · Electrical Eng. & Systems 2022-12-12 Soumi Maiti , Yifan Peng , Takaaki Saeki , Shinji Watanabe

Self-supervised techniques for learning speech representations have been shown to develop linguistic competence from exposure to speech without the need for human labels. In order to fully realize the potential of these approaches and…

We propose a framework to learn semantics from raw audio signals using two types of representations, encoding contextual and phonetic information respectively. Specifically, we introduce a speech-to-unit processing pipeline that captures…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-05 Jaeyeon Kim , Injune Hwang , Kyogu Lee

We describe speaker-independent speech synthesis driven by a small set of phonetically meaningful speech parameters such as formant frequencies. The intention is to leverage deep-learning advances to provide a highly realistic signal…

Audio and Speech Processing · Electrical Eng. & Systems 2023-06-06 Pablo Pérez Zarazaga , Zofia Malisz , Gustav Eje Henter , Lauri Juvela

Generative models are successfully used for image synthesis in the recent years. But when it comes to other modalities like audio, text etc little progress has been made. Recent works focus on generating audio from a generative model in an…

Computer Vision and Pattern Recognition · Computer Science 2018-09-30 Chae Young Lee , Anoop Toffy , Gue Jun Jung , Woo-Jin Han

This study compares the performances of different algorithms for coding speech at low bit rates. In addition to widely deployed traditional vocoders, a selection of recently developed generative-model-based coders at different bit rates are…

Audio and Speech Processing · Electrical Eng. & Systems 2020-03-27 Wissam A. Jassim , Jan Skoglund , Michael Chinen , Andrew Hines

Generative deep neural networks are widely used for speech synthesis, but most existing models directly generate waveforms or spectral outputs. Humans, however, produce speech by controlling articulators, which results in the production of…

Sound · Computer Science 2023-05-10 Gašper Beguš , Alan Zhou , Peter Wu , Gopala K Anumanchipalli

Natural language generation (NLG) is a critical component in a spoken dialogue system. This paper presents a Recurrent Neural Network based Encoder-Decoder architecture, in which an LSTM-based decoder is introduced to select, aggregate…

Computation and Language · Computer Science 2017-08-16 Van-Khanh Tran , Le-Minh Nguyen

The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation learning from raw audio…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-17 Varun Krishna , Tarun Sai , Sriram Ganapathy

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

Computation and Language · Computer Science 2022-05-03 Felix Wu , Kwangyoun Kim , Shinji Watanabe , Kyu Han , Ryan McDonald , Kilian Q. Weinberger , Yoav Artzi

In this paper, we propose a multi-speaker face-to-speech waveform generation model that also works for unseen speaker conditions. Using a generative adversarial network (GAN) with linguistic and speaker characteristic features as auxiliary…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Se-Yun Um , Jihyun Kim , Jihyun Lee , Hong-Goo Kang

Generative models have thrived in computer vision, enabling unprecedented image processes. Yet the results in audio remain less advanced. Our project targets real-time sound synthesis from a reduced set of high-level parameters, including…

Sound · Computer Science 2019-06-25 Adrien Bitton , Philippe Esling , Antoine Caillon , Martin Fouilleul