Search Results for author:
Found 10 papers, 3 papers with code
Training and Inference Efficiency of Encoder-Decoder Speech Models
However, the reported data and compute requirements for their training are prohibitive for many in the research community.
EMMeTT: Efficient Multimodal Machine Translation Training
This work focuses on neural machine translation (NMT) and proposes a joint multimodal training regime of Speech-LLM to include automatic speech translation (AST).
Label-Looping: Highly Efficient Decoding for Transducers
This paper introduces a highly efficient greedy decoding algorithm for Transducer-based speech recognition models.
Speed of Light Exact Greedy Decoding for RNN-T Speech Recognition Models on GPU
The vast majority of inference time for RNN Transducer (RNN-T) models today is spent on decoding.
GPU-Accelerated WFST Beam Search Decoder for CTC-based Speech Recognition
While Connectionist Temporal Classification (CTC) models deliver state-of-the-art accuracy in automated speech recognition (ASR) pipelines, their performance has been limited by CPU-based beam search decoding.
Speech Wikimedia: A 77 Language Multilingual Speech Dataset
The Speech Wikimedia Dataset is a publicly available compilation of audio with transcriptions extracted from Wikimedia Commons.
LSH methods for data deduplication in a Wikipedia artificial dataset
This paper illustrates locality sensitive hasing (LSH) models for the identification and removal of nearly redundant data in a text dataset.
The People's Speech: A Large-Scale Diverse English Speech Recognition Dataset for Commercial Usage
The People's Speech is a free-to-download 30, 000-hour and growing supervised conversational English speech recognition dataset licensed for academic and commercial usage under CC-BY-SA (with a CC-BY subset).
Multiple-Instance, Cascaded Classification for Keyword Spotting in Narrow-Band Audio
We propose using cascaded classifiers for a keyword spotting (KWS) task on narrow-band (NB), 8kHz audio acquired in non-IID environments --- a more challenging task than most state-of-the-art KWS systems face.
Purely sequence-trained neural networks for ASR based on lattice-free MMI
Models trained with LFMMI provide a relative word error rate reduction of ∼11. 5%, over those trained with cross-entropy objective function, and ∼8%, over those trained with cross-entropy and sMBR objective functions.
Ranked #5 on
Speech Recognition
on WSJ eval92
