Exploring Transfer Learning for Urdu Speech Synthesis
Neural methods in Text to Speech synthesis (TTS) have demonstrated momentous advancement in terms of the naturalness and intelligibility of the synthesized speech. In this paper we present neural speech synthesis system for Urdu language, a low resource language. The main challenge faced for this study was the non-availability of any publicly available Urdu speech synthesis corpora. Urdu speech corpus was created using audio books and synthetic speech generation. To leverage the low resource scenario we adopted transfer learning for our experiments where knowledge extracted is further used to train the model using a relatively smaller Urdu training data set. The results from this model show satisfactory results, though a good margin for improvement exists and we are working to improve it further.
Code (0)
등록된 구현이 없습니다.
Tasks
Speech Synthesistext-to-speechText to SpeechText-To-Speech SynthesisTransfer LearningSimilar Papers 제목 키워드 기반
Transfer Learning based Speech Affect Recognition in Urdu
It has been established that Speech Affect Recognition for low resource languages is a difficult task. Here we present a Transfer learning based Speech Affect Recognition approach in which: we pre-train a model for high …
Transfer LearningSTRATA: Word Boundaries & Phoneme Recognition From Continuous Urdu Speech using Transfer Learning, Attention, & Data Augmentation
Phoneme recognition is a largely unsolved problem in NLP, especially for low-resource languages like Urdu. The systems that try to extract the phonemes from audio speech require hand-labeled phonetic transcriptions. This…
Data AugmentationPhoneme RecognitionTransfer LearningStrategies in Transfer Learning for Low-Resource Speech Synthesis: Phone Mapping, Features Input, and Source Language Selection
We compare using a PHOIBLE-based phone mapping method and using phonological features input in transfer learning for TTS in low-resource languages. We use diverse source languages (English, Finnish, Hindi, Japanese, and …
Automatic Speech Recognitionspeech-recognitionSpeech RecognitionSpeech Synthesis+1Exploring Data Augmentation Strategies for Hate Speech Detection in Roman Urdu
In an era where social media platform users are growing rapidly, there has been a marked increase in hateful content being generated; to combat this, automatic hate speech detection systems are a necessity. For this purp…
Data AugmentationHate Speech DetectionCross Lingual Speech Emotion Recognition: Urdu vs. Western Languages
Cross-lingual speech emotion recognition is an important task for practical applications. The performance of automatic speech emotion recognition systems degrades in cross-corpus scenarios, particularly in scenarios invo…
Cross-corpusEmotion RecognitionSpeech Emotion Recognition