Výsledky vyhledávání

A Scalable Model Specialization Framework for Training and Inference using Submodels and its Application to Speech Model Personalization

Autor: Fadi Biadsy, Youzheng Chen, Xia Zhang, Oleg Rybakov, Andrew Rosenberg, Pedro Moreno

Model fine-tuning and adaptation have become a common approach for model specialization for downstream tasks or domains. Fine-tuning the entire model or a subset of the parameters using light-weight adaptation has shown considerable success across di

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5c8583bec2d2cd8544f8535380f04029
http://arxiv.org/abs/2203.12559

Zobrazit plný text záznamu

Extending Parrotron: An End-to-End, Speech Conversion and Speech Recognition Model for Atypical Speech

Autor: Fang Chu, Youzheng Chen, Rohan Doshi, Fadi Biadsy, Xia Zhang, Liyang Jiang, Andrew Rosenberg, Pedro J. Moreno, Bhuvana Ramabhadran

Publikováno v: ICASSP

We present an extended Parrotron model: a single, end-to-end network that enables voice conversion and recognition simultaneously. Input spectrograms are transformed to output spectrograms in the voice of a predetermined target speaker while also gen

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::05999c2348c779fb109133ff6c233288
https://doi.org/10.1109/icassp39728.2021.9414644

Zobrazit plný text záznamu

Comparison of Data Augmentation and Adaptation Strategies for Code-switched Automatic Speech Recognition

Autor: Min Ma, Jesse Emond, Fadi Biadsy, Bhuvana Ramabhadran, Andrew Rosenberg

Publikováno v: ICASSP

Code-switching occurs when the speaker alternates between two or more languages or dialects. It is a pervasive phenomenon in most Indic spoken languages. Code-switching poses a challenge in language modeling as it complicates the orthographic realiza

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::6975ffa69affa2c16a54150b09ac1b4c
https://doi.org/10.1109/icassp.2019.8682824

Zobrazit plný text záznamu

Direct speech-to-speech translation with a sequence-to-sequence model

Autor: Fadi Biadsy, Ye Jia, Melvin Johnson, Zhifeng Chen, Wolfgang Macherey, Yonghui Wu, Ron Weiss

Publikováno v: INTERSPEECH

We present an attention-based sequence-to-sequence neural network which can directly translate speech from one language into speech in another language, without relying on an intermediate text representation. The network is trained end-to-end, learni

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::15becfa04d691db2c4fd7fdf9e739506

Zobrazit plný text záznamu

Parrotron: An End-to-End Speech-to-Speech Conversion Model and its Applications to Hearing-Impaired Speech and Speech Separation

Autor: Ye Jia, Dimitri Kanvesky, Ron Weiss, Pedro J. Moreno, Fadi Biadsy

Publikováno v: INTERSPEECH

We describe Parrotron, an end-to-end-trained speech-to-speech conversion model that maps an input spectrogram directly to another spectrogram, without utilizing any intermediate discrete representation. The network is composed of an encoder, spectrog

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c73b391808afd72766be4ed8cfc5d4d7

Zobrazit plný text záznamu

Modeling Non-Linguistic Contextual Signals in LSTM Language Models Via Domain Adaptation

Autor: Michael Nirschl, Shankar Kumar, Fadi Biadsy, Min Ma, Tomas Vykruta, Pedro J. Moreno

Publikováno v: ICASSP

Language Models (LMs) for Automatic Speech Recognition (ASR) can benefit from utilizing non-linguistic contextual signals in modeling. Examples of these signals include the geographical location of the user speaking to the system and/or the identity

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d7408975e0b72ac2713b90b6aca52822
https://doi.org/10.1109/icassp.2018.8461979

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání