CMU Wilderness Multilingual Speech Dataset. Black, A. W In ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 5971–5975, May, 2019. ISSN: 2379-190Xdoi abstract bibtex This paper describes the CMU Wilderness Multilingual Speech Dataset. A dataset of over 700 different languages providing audio, aligned text and word pronunciations. On average each language provides around 20 hours of sentence-lengthed transcriptions. We describe our multi-pass alignment techniques and evaluate the results by building speech synthesizers on the aligned data. Most of the resulting synthesizers are good enough for deployment and use. The tools to do this work are released as open source, and instructions on how to apply such alignment for novel languages are given.
@inproceedings{black_cmu_2019,
title = {{CMU} {Wilderness} {Multilingual} {Speech} {Dataset}},
doi = {10.1109/ICASSP.2019.8683536},
abstract = {This paper describes the CMU Wilderness Multilingual Speech Dataset. A dataset of over 700 different languages providing audio, aligned text and word pronunciations. On average each language provides around 20 hours of sentence-lengthed transcriptions. We describe our multi-pass alignment techniques and evaluate the results by building speech synthesizers on the aligned data. Most of the resulting synthesizers are good enough for deployment and use. The tools to do this work are released as open source, and instructions on how to apply such alignment for novel languages are given.},
booktitle = {{ICASSP} 2019 - 2019 {IEEE} {International} {Conference} on {Acoustics}, {Speech} and {Signal} {Processing} ({ICASSP})},
author = {Black, Alan W},
month = may,
year = {2019},
note = {ISSN: 2379-190X},
keywords = {Acoustic measurements, Data models, Speech recognition, Speech synthesis, Synthesizers, found speech data, multilingual, speech recognition, speech synthesis},
pages = {5971--5975},
}
Downloads: 0
{"_id":"KnstjmM47SxNHqEKq","bibbaseid":"black-cmuwildernessmultilingualspeechdataset-2019","author_short":["Black, A. W"],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"CMU Wilderness Multilingual Speech Dataset","doi":"10.1109/ICASSP.2019.8683536","abstract":"This paper describes the CMU Wilderness Multilingual Speech Dataset. A dataset of over 700 different languages providing audio, aligned text and word pronunciations. On average each language provides around 20 hours of sentence-lengthed transcriptions. We describe our multi-pass alignment techniques and evaluate the results by building speech synthesizers on the aligned data. Most of the resulting synthesizers are good enough for deployment and use. The tools to do this work are released as open source, and instructions on how to apply such alignment for novel languages are given.","booktitle":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":[{"propositions":[],"lastnames":["Black"],"firstnames":["Alan","W"],"suffixes":[]}],"month":"May","year":"2019","note":"ISSN: 2379-190X","keywords":"Acoustic measurements, Data models, Speech recognition, Speech synthesis, Synthesizers, found speech data, multilingual, speech recognition, speech synthesis","pages":"5971–5975","bibtex":"@inproceedings{black_cmu_2019,\n\ttitle = {{CMU} {Wilderness} {Multilingual} {Speech} {Dataset}},\n\tdoi = {10.1109/ICASSP.2019.8683536},\n\tabstract = {This paper describes the CMU Wilderness Multilingual Speech Dataset. A dataset of over 700 different languages providing audio, aligned text and word pronunciations. On average each language provides around 20 hours of sentence-lengthed transcriptions. We describe our multi-pass alignment techniques and evaluate the results by building speech synthesizers on the aligned data. Most of the resulting synthesizers are good enough for deployment and use. The tools to do this work are released as open source, and instructions on how to apply such alignment for novel languages are given.},\n\tbooktitle = {{ICASSP} 2019 - 2019 {IEEE} {International} {Conference} on {Acoustics}, {Speech} and {Signal} {Processing} ({ICASSP})},\n\tauthor = {Black, Alan W},\n\tmonth = may,\n\tyear = {2019},\n\tnote = {ISSN: 2379-190X},\n\tkeywords = {Acoustic measurements, Data models, Speech recognition, Speech synthesis, Synthesizers, found speech data, multilingual, speech recognition, speech synthesis},\n\tpages = {5971--5975},\n}\n\n","author_short":["Black, A. W"],"key":"black_cmu_2019","id":"black_cmu_2019","bibbaseid":"black-cmuwildernessmultilingualspeechdataset-2019","role":"author","urls":{},"keyword":["Acoustic measurements","Data models","Speech recognition","Speech synthesis","Synthesizers","found speech data","multilingual","speech recognition","speech synthesis"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/mxmplx","dataSources":["aXmRAq63YsH7a3ufx"],"keywords":["acoustic measurements","data models","speech recognition","speech synthesis","synthesizers","found speech data","multilingual","speech recognition","speech synthesis"],"search_terms":["cmu","wilderness","multilingual","speech","dataset","black"],"title":"CMU Wilderness Multilingual Speech Dataset","year":2019}