Výsledky vyhledávání - "Paria Jamshid Lou"

Improving Disfluency Detection by Self-Training a Self-Attentive Model

Publikováno v: ACL
Macquarie University

Self-attentive neural syntactic parsers using contextualized word embeddings (e.g. ELMo or BERT) currently produce state-of-the-art results in joint parsing and disfluency detection in speech transcripts. Since the contextualized word embeddings are

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fecccae2a25203405efd8cebdc92a6b6
https://doi.org/10.18653/v1/2020.acl-main.346

Zobrazit plný text záznamu

End-to-End Speech Recognition and Disfluency Removal

Autor: Mark Johnson, Paria Jamshid Lou

Publikováno v: EMNLP (Findings)
Macquarie University

Disfluency detection is usually an intermediate step between an automatic speech recognition (ASR) system and a downstream task. By contrast, this paper aims to investigate the task of end-to-end speech recognition and disfluency removal. We specific

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a932d7e5504ff3d09d4f86546f002ef5
https://doi.org/10.18653/v1/2020.findings-emnlp.186

Zobrazit plný text záznamu

ShEMO -- A Large-Scale Validated Database for Persian Speech Emotion Detection

Autor: Mansoureh Karami, Omid Mohamad Nezami, Paria Jamshid Lou

This paper introduces a large-scale, validated database for Persian called Sharif Emotional Speech Database (ShEMO). The database includes 3000 semi-natural utterances, equivalent to 3 h and 25 min of speech data extracted from online radio plays. Th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b292621b52d594c1171432dbe6ecbbac
http://arxiv.org/abs/1906.01155

Zobrazit plný text záznamu

Neural Constituency Parsing of Speech Transcripts

Autor: Paria Jamshid Lou, Yufei Wang, Mark Johnson

Publikováno v: NAACL-HLT (1)
Macquarie University

This paper studies the performance of a neural self-attentive parser on transcribed speech. Speech presents parsing challenges that do not appear in written text, such as the lack of punctuation and the presence of speech disfluencies (including fill

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6a20b5ed2d09dcfa8e1124ad2cd98a17
https://doi.org/10.18653/v1/n19-1282

Zobrazit plný text záznamu

Disfluency Detection using a Noisy Channel Model and a Deep Neural Language Model

Autor: Paria Jamshid Lou, Mark Johnson

Publikováno v: ACL (2)

This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) la

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fad523dbbb1f4c63e31d3aa047319889
http://arxiv.org/abs/1808.09091

Zobrazit plný text záznamu

Disfluency Detection using Auto-Correlational Neural Networks

Autor: Mark Johnson, Paria Jamshid Lou, Peter Anderson

Publikováno v: EMNLP
Macquarie University

In recent years, the natural language processing community has moved away from task-specific feature engineering, i.e., researchers discovering ad-hoc feature representations for various tasks, in favor of general-purpose methods that learn the input

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::42220f3ddb115841400855af1b98d183

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání