相关论文: Prosody Labelled Dataset for Hindi using Semi-Auto…
A crucial step in processing speech audio data for information extraction, topic detection, or browsing/playback is to segment the input into sentence and topic units. Speech segmentation is challenging, since the cues typically present for…
Being less resource languages, Indian-Indian and English-Indian language MT system developments faces the difficulty to translate various lexical phenomena. In this paper, we present our work on a comparative study of 440 phrase-based…
Speech translation for Indian languages remains a challenging task due to the scarcity of large-scale, publicly available datasets that capture the linguistic diversity and domain coverage essential for real-world applications. Existing…
The long-standing goal of Artificial Intelligence (AI) has been to create human-like conversational systems. Such systems should have the ability to develop an emotional connection with the users, hence emotion recognition in dialogues is…
Prosody contains rich information beyond the literal meaning of words, which is crucial for the intelligibility of speech. Current models still fall short in phrasing and intonation; they not only miss or misplace breaks when synthesizing…
Text-to-speech is now able to achieve near-human naturalness and research focus has shifted to increasing expressivity. One popular method is to transfer the prosody from a reference speech sample. There have been considerable advances in…
This paper analyzes dysarthric speech datasets from three languages with different prosodic systems: English, Korean, and Tamil. We inspect 39 acoustic measurements which reflect three speech dimensions including voice quality,…
Speech deepfake detection (SDD) systems perform well on standard benchmarks datasets but often fail to generalize to expressive and emotional spoofing attacks. Many methods rely on spoof-heavy training data, learning dataset-specific…
State-of-the-art text-to-speech (TTS) systems realize high naturalness in monolingual environments, synthesizing speech with correct multilingual accents (especially for Indic languages) and context-relevant emotions still poses difficulty…
The problem of audio-to-text alignment has seen significant amount of research using complete supervision during training. However, this is typically not in the context of long audio recordings wherein the text being queried does not appear…
We present ProsAudit, a benchmark in English to assess structural prosodic knowledge in self-supervised learning (SSL) speech models. It consists of two subtasks, their corresponding metrics, and an evaluation dataset. In the protosyntax…
Standard text-to-speech (TTS) evaluation measures intelligibility (WER, CER) and overall naturalness (MOS, UTMOS) but does not quantify accent. A synthesiser may score well on all four yet sound non-native on features that are phonemic in…
Hindi being a highly inflectional language, FST (Finite State Transducer) based approach is most efficient for developing a morphological analyzer for this language. The work presented in this paper uses the SFST (Stuttgart Finite State…
Hindi, one of the most spoken language of India, exhibits a diverse array of accents due to its usage among individuals from diverse linguistic origins. To enable a robust evaluation of Hindi ASR systems on multiple accents, we create a…
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…
Recent advancements in end-to-end speech synthesis have made it possible to generate highly natural speech. However, training these models typically requires a large amount of high-fidelity speech data, and for unseen texts, the prosody of…
Large language models (LLMs) demonstrated transformative capabilities in many applications that require automatically generating responses based on human instruction. However, the major challenge for building LLMs, particularly in Indic…
Speech fluency/disfluency can be evaluated by analyzing a range of phonetic and prosodic features. Deep neural networks are commonly trained to map fluency-related features into the human scores. However, the effectiveness of deep…
Recent advancements in neural end-to-end TTS models have shown high-quality, natural synthesized speech in a conventional sentence-based TTS. However, it is still challenging to reproduce similar high quality when a whole paragraph is…
Traditional models of accent perception underestimate the role of gradient variations in phonological features which listeners rely upon for their accent judgments. We investigate how pretrained representations from current self-supervised…