Accent Conversion Using Phonetic Posteriorgrams

Zhao, Guanlong; Sonsaat, Sinem; Levis, John M.; Chukharev‐Hudilainen, Evgeny; Gutierrez‐Osuna, Ricardo

doi:10.1109/icassp.2018.8462258

Cited by 43 publications

(28 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PPG-GMM: a state-of-the-art GMM-based non-parallel VC framework [27]. The approach extracts a phonetic posteriorgram (PPG) for each frame in the source and target speaker corpus.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion

Ding

Gutierrez‐Osuna

2019

Interspeech 2019

Self Cite

View full text Add to dashboard Cite

This paper proposes a Group Latent Embedding for Vector Quantized Variational Autoencoders (VQ-VAE) used in nonparallel Voice Conversion (VC). Previous studies have shown that VQ-VAE can generate high-quality VC syntheses when it is paired with a powerful decoder. However, in a conventional VQ-VAE, adjacent atoms in the embedding dictionary can represent entirely different phonetic content. Therefore, the VC syntheses can have mispronunciations and distortions whenever the output of the encoder is quantized to an atom representing entirely different phonetic content. To address this issue, we propose an approach that divides the embedding dictionary into groups and uses the weighted average of atoms in the nearest group as the latent embedding. We conducted both objective and subjective experiments on the non-parallel CSTR VCTK corpus. Results show that the proposed approach significantly improves the acoustic quality of the VC syntheses compared to the traditional VQ-VAE (13.7% relative improvement) while retaining the voice identity of the target speaker.

show abstract

“…PPG-GMM: a state-of-the-art GMM-based non-parallel VC framework [27]. The approach extracts a phonetic posteriorgram (PPG) for each frame in the source and target speaker corpus.…”

Section: Resultsmentioning

confidence: 99%

“…To avoid the laborious process of collecting parallel corpora, several non-parallel VC techniques have been proposed in recent years. These include the INCA algorithm [23], DNNs [24,25], sparse representations [26], and phonetic posteriorgrams [27]. More recently, Hsu et al [12,28] proposed to use a VAE for VC.…”

Section: Literature Reviewmentioning

confidence: 99%

Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion

Ding

Gutierrez‐Osuna

2019

Interspeech 2019

Self Cite

View full text Add to dashboard Cite

show abstract

“…To overcome the insufficiencies outlined above, we constructed (and are now releasing) L2-ARCTIC to provide an open corpus for voice conversion between accented speakers, accent conversion, and mispronunciation detection. Zhao et al [26] have performed a preliminary evaluation on voice/accent conversion tasks using a subset of the speakers in L2-ARCTIC. Using a joint-density GMM with MLPG and global variance compensation [9] (128 mixtures, ~5 min of parallel training data) as the voice conversion system, they obtained 2.5 Mean Opinion Score (MOS) on the converted speech, which was also rated as similar to the target voice.…”

Section: The Need For a New L2 English Corpusmentioning

confidence: 99%

L2-ARCTIC: A Non-native English Speech Corpus

Zhao¹,

Sonsaat²,

Silpachai³

et al. 2018

Interspeech 2018

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce L2-ARCTIC, a speech corpus of non-native English that is intended for research in voice conversion, accent conversion, and mispronunciation detection. This initial release includes recordings from ten non-native speakers of English whose first languages (L1s) are Hindi, Korean, Mandarin, Spanish, and Arabic, each L1 containing recordings from one male and one female speaker. Each speaker recorded approximately one hour of read speech from the Carnegie Mellon University ARCTIC prompts, from which we generated orthographic and forced-aligned phonetic transcriptions. In addition, we manually annotated 150 utterances per speaker to identify three types of mispronunciation errors: substitutions, deletions, and additions, making it a valuable resource not only for research in voice conversion and accent conversion but also in computer-assisted pronunciation training. The corpus is publicly accessible at https://psi.engr.tamu.edu/l2-arctic-corpus/.

show abstract

“…Voice transformation (VT) is a technique to modify some properties of human speech while preserving its linguistic information. VT can be applied to change the speaker identity, i.e., voice conversion (VC) [1], or to transform the speaking style of a speaker, such as emotion and accent conversion [2]. In this work, we will focus on emotion voice transformation.…”

Section: Introductionmentioning

confidence: 99%

Nonparallel Emotional Speech Conversion

Gao

Chakraborty²,

Tembiné³

et al. 2019

Interspeech 2019

View full text Add to dashboard Cite

We propose a nonparallel data-driven emotional speech conversion method. It enables the transfer of emotion-related characteristics of a speech signal while preserving the speaker's identity and linguistic content. Most existing approaches require parallel data and time alignment, which is not available in many real applications. We achieve nonparallel training based on an unsupervised style transfer technique, which learns a translation model between two distributions instead of a deterministic one-to-one mapping between paired examples. The conversion model consists of an encoder and a decoder for each emotion domain. We assume that the speech signal can be decomposed into an emotion-invariant content code and an emotion-related style code in latent space. Emotion conversion is performed by extracting and recombining the content code of the source speech and the style code of the target emotion. We tested our method on a nonparallel corpora with four emotions. The evaluation results show the effectiveness of our approach.

show abstract

Accent Conversion Using Phonetic Posteriorgrams

Cited by 43 publications

References 16 publications

Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion

Group Latent Embedding for Vector Quantized Variational Autoencoder in Non-Parallel Voice Conversion

L2-ARCTIC: A Non-native English Speech Corpus

Nonparallel Emotional Speech Conversion

Contact Info

Product

Resources

About