G Sanjay

Bio: G Sanjay is an academic researcher. The author has contributed to research in topics: Speech synthesis & Transformer (machine learning model). The author has co-authored 1 publications.

Natural Text-to-Speech Synthesis by Conditioning Spectrogram Predictions from Transformer Network on WaveGlow Vocoder

Abstract: Text to Speech (TTS) is a form of speech synthesis where the text is converted into a spoken human-like voice output. The state of the art methods for TTS employs a neural network based approach. This work aims to look at some of the issues and limitations present in the current works, specifically Tacotron-2, and attempts to further improve its performance by modifying its architecture. The modified model uses Transformer network as a Spectrogram Prediction Network (SPN) and WaveGlow as an Audio Generation Network (AGN). For the modified model, performance improvements are seen in terms of the speech output generated for corresponding texts, the inference time taken for audio generation, and a Mean Opinion Score (MOS) of 4.10 (out of 5) is obtained.

Spoofing-Aware Speaker Verification with Unsupervised Domain Adaptation

Abstract: In this paper, we initiate the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module. We start from the standard ASV framework of the ASVspoof 2019 baseline and approach the problem from the back-end classifier based on probabilistic linear discriminant analysis. We employ three unsupervised domain adaptation techniques to optimize the back-end using the audio data in the training partition of the ASVspoof 2019 dataset. We demonstrate notable improvements on both logical and physical access scenarios, especially on the latter where the system is attacked by replayed audios, with a maximum of 36.1% and 5.3% relative improvement on bonafide and spoofed cases, respectively. We perform additional studies such as per-attack breakdown analysis, data composition, and integration with a countermeasure system at score-level with Gaussian back-end.

Bi-Sep: A Multi-Resolution Cross-Domain Monaural Speech Separation Framework

Abstract: In recent years, deep neural network (DNN)-based time-domain methods for monaural speech separation have substantially improved under an anechoic condition. However, the performance of these methods degrades when facing harsher conditions, such as noise or reverberation. Although adopting Short-Time Fourier Transform (STFT) for feature extraction of these neural methods helps stabilize the performance in non-anechoic situations, it inherently loses the fine-grained vision, which is one of the particularities of time-domain methods. Therefore, this study explores incorporating time and STFT-domain features to retain their beneficial characteristics. Furthermore, we leverage a Bi-Projection Fusion (BPF) mechanism to merge the information between two domains. To evaluate the effectiveness of our proposed method, we conduct experiments in an anechoic setting on the WSJ0-2mix dataset and noisy/reverberant settings on WHAM!/WHAMR! dataset. The experiment shows that with a cost of ignorable degradation on anechoic dataset, the proposed method manages to promote the performance of existing neural models when facing more complicated environments.