English
Related papers

Related papers: Provable Speech Attributes Conversion via Latent I…

200 papers

To address the performance gap of English ASR models on L2 English speakers, we evaluate fine-tuning of pretrained wav2vec 2.0 models (Baevski et al., 2020; Xu et al., 2021) on L2-ARCTIC, a non-native English speech corpus (Zhao et al.,…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-18 Toshiko Shibano , Xinyi Zhang , Mia Taige Li , Haejin Cho , Peter Sullivan , Muhammad Abdul-Mageed

Spoken language understanding system is traditionally designed as a pipeline of a number of components. First, the audio signal is processed by an automatic speech recognizer for transcription or n-best hypotheses. With the recognition…

Computation and Language · Computer Science 2018-02-26 Dmitriy Serdyuk , Yongqiang Wang , Christian Fuegen , Anuj Kumar , Baiyang Liu , Yoshua Bengio

In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Paul-Gauthier Noé , Mohammad Mohammadamini , Driss Matrouf , Titouan Parcollet , Andreas Nautsch , Jean-François Bonastre

In speech recognition, it is essential to model the phonetic content of the input signal while discarding irrelevant factors such as speaker variations and noise, which is challenging in low-resource settings. Self-supervised pre-training…

Computation and Language · Computer Science 2023-01-04 Sreepratha Ram , Hanan Aldarmaki

We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…

Sound · Computer Science 2024-12-24 Prateek Verma , Chris Chafe

While the general idea of self-supervised learning is identical across modalities, the actual algorithms and objectives differ widely because they were developed with a single modality in mind. To get us closer to general self-supervised…

Machine Learning · Computer Science 2022-10-27 Alexei Baevski , Wei-Ning Hsu , Qiantong Xu , Arun Babu , Jiatao Gu , Michael Auli

We present a method for converting the voices between a set of speakers. Our method is based on training multiple autoencoder paths, where there is a single speaker-independent encoder and multiple speaker-dependent decoders. The…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-13 Orhan Ocal , Oguz H. Elibol , Gokce Keskin , Cory Stephenson , Anil Thomas , Kannan Ramchandran

This work presents a framework based on feature disentanglement to learn speaker embeddings that are robust to environmental variations. Our framework utilises an auto-encoder as a disentangler, dividing the input speaker embedding into…

Sound · Computer Science 2024-06-21 KiHyun Nam , Hee-Soo Heo , Jee-weon Jung , Joon Son Chung

We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-11 Manuel Sam Ribeiro , Julian Roth , Giulia Comini , Goeric Huybrechts , Adam Gabrys , Jaime Lorenzo-Trueba

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

Audio and Speech Processing · Electrical Eng. & Systems 2025-01-14 Yusuf Brima , Ulf Krumnack , Simone Pika , Gunther Heidemann

Traditional voice conversion(VC) has been focused on speaker identity conversion for speech with a neutral expression. We note that emotional expression plays an essential role in daily communication, and the emotional style of speech can…

Audio and Speech Processing · Electrical Eng. & Systems 2021-10-22 Zongyang Du , Berrak Sisman , Kun Zhou , Haizhou Li

This paper describes representations of time-dependent signals that are invariant under any invertible time-independent transformation of the signal time series. Such a representation is created by rescaling the signal in a non-linear…

Computation and Language · Computer Science 2007-05-23 David N. Levin

A key goal of unsupervised representation learning is "inverting" a data generating process to recover its latent properties. Existing work that provably achieves this goal relies on strong assumptions on relationships between the latent…

Machine Learning · Computer Science 2021-11-01 Kartik Ahuja , Jason Hartford , Yoshua Bengio

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Computation and Language · Computer Science 2021-10-11 Kemal Kurniawan , Lea Frermann , Philip Schulz , Trevor Cohn

Variational autoencoder-based voice conversion (VAE-VC) has the advantage of requiring only pairs of speeches and speaker labels for training. Unlike the majority of the research in VAE-VC which focuses on utilizing auxiliary losses or…

Sound · Computer Science 2021-12-07 Kei Akuzawa , Kotaro Onishi , Keisuke Takiguchi , Kohki Mametani , Koichiro Mori

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

Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of "style tokens" in…

Computation and Language · Computer Science 2017-11-03 Yuxuan Wang , RJ Skerry-Ryan , Ying Xiao , Daisy Stanton , Joel Shor , Eric Battenberg , Rob Clark , Rif A. Saurous

In this paper our goal is to convert a set of spoken lines into sung ones. Unlike previous signal processing based methods, we take a learning based approach to the problem. This allows us to automatically model various aspects of this…

Audio and Speech Processing · Electrical Eng. & Systems 2020-02-18 Jayneel Parekh , Preeti Rao , Yi-Hsuan Yang

In recent years, developing a speech understanding system that classifies a waveform to structured data, such as intents and slots, without first transcribing the speech to text has emerged as an interesting research problem. This work…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Mohamed Mhiri , Samuel Myer , Vikrant Singh Tomar

Supervised training of abstractive language generation models results in learning conditional probabilities over language sequences based on the supervised training signal. When the training signal contains a variety of writing styles, such…

Computation and Language · Computer Science 2018-04-12 Ye Zhang , Nan Ding , Radu Soricut