1 code implementation • 6 Apr 2024 • Yingting Li, Rishabh Bhardwaj, Ambuj Mehrish, Bo Cheng, Soujanya Poria
In this work, we present HyperTTS, which comprises a small learnable network, "hypernetwork", that generates parameters of the Adapter blocks, allowing us to condition Adapters on speaker representations and making them dynamic.
1 code implementation • 31 Mar 2024 • Xiang Li, Fan Bu, Ambuj Mehrish, Yingting Li, Jiale Han, Bo Cheng, Soujanya Poria
The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech synthesis.
1 code implementation • 29 May 2023 • Ambuj Mehrish, Abhinav Ramesh Kashyap, Li Yingting, Navonil Majumder, Soujanya Poria
There are significant challenges for speaker adaptation in text-to-speech for languages that are not widely spoken or for speakers with accents or dialects that are not well-represented in the training data.
no code implementations • 30 Apr 2023 • Ambuj Mehrish, Navonil Majumder, Rishabh Bhardwaj, Rada Mihalcea, Soujanya Poria
The power of deep learning techniques has opened up new avenues for research and innovation in the field of speech processing, with far-reaching implications for a range of industries and applications.
1 code implementation • 24 Apr 2023 • Deepanway Ghosal, Navonil Majumder, Ambuj Mehrish, Soujanya Poria
The immense scale of the recent large language models (LLM) allows many interesting properties, such as, instruction- and chain-of-thought-based fine-tuning, that has significantly improved zero- and few-shot performance in many natural language processing (NLP) tasks.
Ranked #4 on Audio Generation on AudioCaps
1 code implementation • 2 Mar 2023 • Yingting Li, Ambuj Mehrish, Shuai Zhao, Rishabh Bhardwaj, Amir Zadeh, Navonil Majumder, Rada Mihalcea, Soujanya Poria
To mitigate this issue, parameter-efficient transfer learning algorithms, such as adapters and prefix tuning, have been proposed as a way to introduce a few trainable parameters that can be plugged into large pre-trained language models such as BERT, and HuBERT.
1 code implementation • 7 Nov 2022 • Jan Melechovsky, Ambuj Mehrish, Berrak Sisman, Dorien Herremans
Accent plays a significant role in speech communication, influencing understanding capabilities and also conveying a person's identity.