Discovering the phoneme inventory of an unwritten language: A machine-assisted approach

Kempton, Timothy; Moore, Roger K.

doi:10.1016/j.specom.2013.02.006

Cited by 15 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Today, there exist many methods to automatically discover an phone inventory. This is not the same as a linguistically-motivated phonemic inventory, but findings in [3] suggest that it makes a functional approximate. Many approaches to identifying this inventory involve cross lingual transfer from high-resource languages to lowerresource ones.…”

Section: Related Workmentioning

confidence: 91%

See 1 more Smart Citation

Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages

Hillis¹,

Kumar²,

Black

2019

Interspeech 2019

View full text Add to dashboard Cite

We experiment with unsupervised methods for deriving and clustering symbolic representations of speech, working towards speech-to-speech translation for languages without regular (or any) written representations. We consider five low-resource African languages, and we produce three different segmental representations of text data for comparisons against four different segmental representations derived solely from acoustic data for each language. The text and speech data for each language comes from the CMU Wilderness dataset introduced in [1], where speakers read a version of the New Testament in their language. Our goal is to evaluate the translation performance not only of acoustically derived units but also of discovered sequences or "words" made from these units, with the intuition that such representations will encode more meaning than phones alone. We train statistical machine translation models for each representation and evaluate their outputs on the basis of BLEU-1 scores to determine their efficacy. Our experiments produce encouraging results: as we cluster our atomic phonetic representations into more word-like units, the amount information retained generally approaches that of the actual words themselves.

show abstract

Section: Related Workmentioning

confidence: 91%

“…https://bergvca.github.io/2017/10/14/super-fast-stringmatching.html3 https://github.com/epfml/sent2vec.git…”

mentioning

confidence: 99%

Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages

Hillis¹,

Kumar²,

Black

2019

Interspeech 2019

View full text Add to dashboard Cite

show abstract

“…A small number of studies have specifically explored the problem of discovering the phoneme inventory of an unwritten language [10]. The goal of phoneme discovery studies is not merely to discover acoustic units in the target language, but to associate each discovered unit with an IPA phone symbol, so that it is possible to generate an IPA phonetic transcription of speech in the target language without using any information about the (possibly non-existent) orthography of the target language.…”

Section: Prior Work: Zero-resourced Speech Recognitionmentioning

confidence: 99%

Mismatched Crowdsourcing from Multiple Annotator Languages for Recognizing Zero-Resourced Languages: A Nullspace Clustering Approach

et al. 2017

View full text Add to dashboard Cite

It is extremely challenging to create training labels for building acoustic models of zero-resourced languages, in which conventional resources required for model training -lexicons, transcribed audio, or in extreme cases even orthographic system or a viable phone set design for the language -are unavailable. Here, language mismatched transcripts, in which audio is transcribed in the orthographic system of a completely different language by possibly non-speakers of the target language may play a vital role. Such mismatched transcripts have recently been successfully obtained through crowdsourcing and shown to be beneficial to ASR performance. This paper further studies this problem of using mismatched crowdsourced transcripts in a tonal language for which we have no standard orthography, and in which we may not even know the phoneme inventory. It proposes methods to project the multilingual mismatched transcriptions of a tonal language to the target phone segments. The results tested on Cantonese and Singapore Hokkien have shown that the reconstructed phone sequences' accuracies have absolute increment of more than 3% from those of previously proposed monolingual probabilistic transcription methods.

show abstract

“…Recently, there has been a growing interest in developing technologies for low-resource languages 1 . A variety of approaches have been proposed, from such as bootstrapping with models from well-resourced languages to complete self-discovery of linguistic units for unwritten languages (see for example [14,20,22]).…”

Section: Introductionmentioning

confidence: 99%

Investigating techniques for low resource conversational speech recognition

Laurent

Fraga-Silva

Lamel

et al. 2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this paper we investigate various techniques in order to build effective speech to text (STT) and keyword search (KWS) systems for low resource conversational speech. Subword decoding and graphemic mappings were assessed in order to detect out-of-vocabulary keywords. To deal with the limited amount of transcribed data, semi-supervised training and data selection methods were investigated. Robust acoustic features produced via data augmentation were evaluated for acoustic modeling. For language modeling, automatically retrieved conversational-like Webdata was used, as well as neural network based models. We report STT improvements with all the techniques, but interestingly only some improve KWS performance. Results are reported for the Swahili language in the context of the 2015 OpenKWS Evaluation.

show abstract

Discovering the phoneme inventory of an unwritten language: A machine-assisted approach

Cited by 15 publications

References 11 publications

Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages

Unsupervised Phonetic and Word Level Discovery for Speech to Speech Translation for Unwritten Languages

Mismatched Crowdsourcing from Multiple Annotator Languages for Recognizing Zero-Resourced Languages: A Nullspace Clustering Approach

Investigating techniques for low resource conversational speech recognition

Contact Info

Product

Resources

About