English
Related papers

Related papers: Exploring Phoneme-Level Speech Representations for…

200 papers

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…

Computation and Language · Computer Science 2021-04-21 Wei Zhou , Simon Berger , Ralf Schlüter , Hermann Ney

One of the main challenges for end-to-end speech translation is data scarcity. We leverage pseudo-labels generated from unlabeled audio by a cascade and an end-to-end speech translation model. This provides 8.3 and 5.7 BLEU gains over a…

Computation and Language · Computer Science 2020-10-14 Juan Pino , Qiantong Xu , Xutai Ma , Mohammad Javad Dousti , Yun Tang

This paper explores the idea of using phonemes as a textual representation within a conventional multilingual simultaneous speech-to-speech translation pipeline, as opposed to the traditional reliance on text-based language representations.…

Machine Learning · Computer Science 2025-04-24 Rene Pilz , Johannes Schneider

Recovering the masked speech frames is widely applied in speech representation learning. However, most of these models use random masking in the pre-training. In this work, we proposed two kinds of masking approaches: (1) speech-level…

Sound · Computer Science 2022-10-26 Xulong Zhang , Jianzong Wang , Ning Cheng , Kexin Zhu , Jing Xiao

Neural models have become ubiquitous in automatic speech recognition systems. While neural networks are typically used as acoustic models in more complex systems, recent studies have explored end-to-end speech recognition systems based on…

Computation and Language · Computer Science 2017-09-15 Yonatan Belinkov , James Glass

This research optimizes two-pass cross-lingual transfer learning in low-resource languages by enhancing phoneme recognition and phoneme-to-grapheme translation models. Our approach optimizes these two stages to improve speech recognition…

Computation and Language · Computer Science 2023-12-07 Wonjun Lee , Gary Geunbae Lee , Yunsu Kim

Language models are typically trained on large corpora of text in their default orthographic form. However, this is not the only option; representing data as streams of phonemes can offer unique advantages, from deeper insights into…

Computation and Language · Computer Science 2024-10-31 Zébulon Goriely , Richard Diehl Martinez , Andrew Caines , Lisa Beinborn , Paula Buttery

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Computation and Language · Computer Science 2022-10-20 Changhan Wang , Hirofumi Inaguma , Peng-Jen Chen , Ilia Kulikov , Yun Tang , Wei-Ning Hsu , Michael Auli , Juan Pino

End-to-end speech-to-text translation can provide a simpler and smaller system but is facing the challenge of data scarcity. Pre-training methods can leverage unlabeled data and have been shown to be effective on data-scarce settings. In…

Audio and Speech Processing · Electrical Eng. & Systems 2020-10-27 Anne Wu , Changhan Wang , Juan Pino , Jiatao Gu

When building state-of-the-art speech translation models, the need for large computational resources is a significant obstacle due to the large training data size and complex models. The availability of pre-trained models is a promising…

Computation and Language · Computer Science 2022-11-10 Zhaolin Li , Jan Niehues

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

Sequence-to-sequence translation methods based on generation with a side-conditioned language model have recently shown promising results in several tasks. In machine translation, models conditioned on source side words have been used to…

Computation and Language · Computer Science 2015-08-21 Kaisheng Yao , Geoffrey Zweig

It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation. Although these mined corpora are large in volume, their quality is questionable. This work shows…

Computation and Language · Computer Science 2024-02-06 Md Mahfuz Ibn Alam , Antonios Anastasopoulos

Approaches to improving multilingual language understanding often struggle with significant performance gaps between high-resource and low-resource languages. While there are efforts to align the languages in a single latent space to…

Computation and Language · Computer Science 2024-11-18 Haeji Jung , Changdae Oh , Jooeon Kang , Jimin Sohn , Kyungwoo Song , Jinkyu Kim , David R. Mortensen

In the traditional cascading architecture for spoken language understanding (SLU), it has been observed that automatic speech recognition errors could be detrimental to the performance of natural language understanding. End-to-end (E2E) SLU…

Computation and Language · Computer Science 2021-09-02 Qian Chen , Wen Wang , Qinglin Zhang

Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…

Sound · Computer Science 2021-03-18 Jeff Donahue , Sander Dieleman , Mikołaj Bińkowski , Erich Elsen , Karen Simonyan

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder. This leads to a significant training gap between pre-training and fine-tuning, largely due to the modality…

Computation and Language · Computer Science 2022-07-05 Jinming Zhao , Hao Yang , Ehsan Shareghi , Gholamreza Haffari

End-to-end neural network systems for automatic speech recognition (ASR) are trained from acoustic features to text transcriptions. In contrast to modular ASR systems, which contain separately-trained components for acoustic modeling,…

Computation and Language · Computer Science 2020-04-21 Yonatan Belinkov , Ahmed Ali , James Glass

While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…

Sound · Computer Science 2025-09-22 Ryan Collette , Ross Greenwood , Serena Nicoll

End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR). One of their advantages is the simplicity of building that directly recognizes the speech frame sequence into the text label sequence by…

Audio and Speech Processing · Electrical Eng. & Systems 2020-05-26 Linhao Dong , Cheng Yi , Jianzong Wang , Shiyu Zhou , Shuang Xu , Xueli Jia , Bo Xu
‹ Prev 1 2 3 10 Next ›