Using Phonetic Posteriorgram Based Frame Pairing for Segmental Accent Conversion

Zhao, Guanlong; Gutierrez‐Osuna, Ricardo

doi:10.1109/taslp.2019.2926754

Cited by 13 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section briefly describes the most popular datasets for accent conversion. Librispeech [4] is often used for training intermediary models, such as acoustic models [5]- [7] or from pre-trained models [8], [9]. It has more than English speech from 1,166 speakers, with pre-built language models and data for training language models.…”

Section: A Literature Reviewmentioning

confidence: 99%

Automatic Collection of Transcribed Speech for Low Resources Languages

Lima

Abreu

2023

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)

View full text Add to dashboard Cite

Speech is a crucial for human communication and combined with the evolution of instant messaging in voice format as well as automated chatbots, its importance is greater. While the majority of speech technologies have achieved high accuracy, they fail when tested for accents that deviate from the "standard" of a language. This becomes more concerning for languages that lack on datasets and have scarce literature, like Brazilian Portuguese. Thus, this paper proposes a methodology to collect and release a speech dataset for Brazilian Portuguese. The method explores the availability of data and information in video platforms, and automatically extracts the audio from TEDx Talks.

show abstract

Section: A Literature Reviewmentioning

confidence: 99%

Automatic Collection of Transcribed Speech for Low Resources Languages

Lima

Abreu

2023

2023 IEEE 13th International Conference on Pattern Recognition Systems (ICPRS)

View full text Add to dashboard Cite

show abstract

“…from an ASR system) to estimate the posterior probability that each frame belongs to a set of pre-defined phonetic units (e.g., a phonetic posteriorgram, or PPG [27]). Once a PPG has been computed for each source and target frame in the corpus, the two can be paired in a many-to-many fashion based on the similarity between their respective PPGs [5,28].…”

Section: Accent Conversionmentioning

confidence: 99%

“…In this work, we propose a new methodology to examine the role of accent and voice quality in talker recognition. Our methodology relies on the use of "accent conversion" techniques [5,6] to transform utterances from second-language (L2) learners 1 to mimic the pronunciation patterns (i.e., accent) of a native (L1) speaker, and vice versa. Our accent conversion model consists of three basic components: an acoustic model that generates a speaker-independent embedding of an utterance (a posteriorgram, or PPG), a sequence-to-sequence (seq2seq) synthesizer that maps PPGs into Mel-spectrograms, and a vocoder that maps the Mel-spectrogram into a highquality speech waveform.…”

Section: Introductionmentioning

confidence: 99%

Understanding the Effect of Voice Quality and Accent on Talker Similarity

Das¹,

Zhao²,

Levis³

et al. 2020

Interspeech 2020

Self Cite

View full text Add to dashboard Cite

This paper presents a methodology to study the role of nonnative accents on talker recognition by humans. The methodology combines a state-of-the-art accent-conversion system to resynthesize the voice of a speaker with a different accent of her/his own, and a protocol for perceptual listening tests to measure the relative contribution of accent and voice quality on speaker similarity. Using a corpus of nonnative and native speakers, we generated accent conversions in two different directions: non-native speakers with native accents, and native speakers with non-native accents. Then, we asked listeners to rate the similarity between 50 pairs of real or synthesized speakers. Using a linear mixed effects model, we find that (for our corpus) the effect of voice quality is five times as large as that of non-native accent, and that the effect goes away when speakers share the same (native) accent. We discuss the potential significance of this work in earwitness identification and sociophonetics.

show abstract