Enhancing and Adversarial: Improve ASR with Speaker Labels

11 November 2022

Papers citing "Enhancing and Adversarial: Improve ASR with Speaker Labels"

4 / 4 papers shown

Title
Dynamic Encoder Size Based on Data-Driven Layer-wise Pruning for Speech Recognition Jingjing Xu Wei Zhou Zijian Yang Eugen Beck Ralf Schlueter 18 1 0 10 Jul 2024
PI-Whisper: An Adaptive and Incremental ASR Framework for Diverse and Evolving Speaker Characteristics Amir Nassereldine Dancheng Liu Chenhui Xu Jinjun Xiong 36 0 0 21 Jun 2024
Accented Speech Recognition With Accent-specific Codebooks Darshan Prabhu P. Jyothi Sriram Ganapathy Vinit Unni 32 7 0 24 Oct 2023
On-Device Speaker Anonymization of Acoustic Embeddings for ASR based onFlexible Location Gradient Reversal Layer Md. Asif Jalal Pablo Peso Parada Jisi Zhang Karthikeyan P. Saravanan Mete Ozay Myoungji Han Jung In Lee Seokyeong Jung 17 1 0 25 Jul 2023