Titlebook: Speech and Computer; 25th International C Alexey Karpov,K. Samudravijaya,S. R. Mahadeva Pras Conference proceedings 2023 The Editor(s) (if

Lasting

Phone Durations Modeling for Livvi-Karelian ASRnguage (Livvi-Karelian dialect). The main issues addressed within this work are related to acoustic modeling, viz. the treatment of long and short phonemes. There are two approaches to modeling phonological duration in the so-called quantity languages: representation of long and short phonemes as di

鸽子

Tractable

Study of Various End-to-End Keyword Spotting Systems on the Bengali Language Under Low-Resource Condvarious keyword techniques in the Indian regional Bengali language under low-resource conditions. In this context, we study several KWS techniques which are common in the English language in Bengali namely: Conv1D, Conv2D+attention, Conv2D+multi head attention, VGG, Dense-net, and Vision transformer

删减

Bridging the Gap: Towards Linguistic Resource Development for the Low-Resource Lambani Languagestic resources makes it challenging for technology development of under-resource languages. This paper aims at developing linguistic tools for Lambamni, an under-resourced tribal language of India through corpora creation, annotation, and transfer learning from contact language. Based on the annotat

Asparagus

Studying the Effect of Frame-Level Concatenation of GFCC and TS-MFCC Features on Zero-Shot Children’catenation of two complementary front-end acoustic features. The acoustic features chosen are TANDEM-STRAIGHT-based Mel-frequency cepstral coefficients (TS-MFCC) and Gamma-tone frequency cepstral coefficients (GFCC). The GFCC model the cochlear response of the human auditory system. The MFCC feature

联邦

奇思怪想

Herd-Immunity

An ASR Corpus in Chhattisgarhi, a Low Resource Indian Language including Chhattisgarhi. The paper elaborates on the entire process of such a low-resource database preparation in a crowd-sourced manner. Through this work we have open-sourced around 250 h of dialect-rich, domain-rich Chhattisgarhi ASR dataset to popularize the scope of voice technology to the Ch

ARY

Cross Lingual Style Transfer Using Multiscale Loss Function for Soliga: A Low Resource Tribal Langua on a multi-scale loss function, using a deep learning framework for syntactically similar languages Kannada and Soliga, under a low resource setup. The existing speaker adaptation methods usually depend on monolingual data and cannot be directly adopted for cross-lingual data. The proposed method c

degradation