Search Results for author:
Found 10 papers, 0 papers with code
Delayed Fusion: Integrating Large Language Models into First-Pass Decoding in End-to-end Speech Recognition
We propose "delayed fusion," which applies LLM scores to ASR hypotheses with a delay during decoding and enables easier use of pre-trained LLMs in ASR tasks.
Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval
However, the biasing mechanism is typically based on a cross-attention module between the audio and a catalogue of biasing entries, which means computational complexity can pose severe practical limitations on the size of the biasing catalogue and consequently on accuracy improvements.
Focused Discriminative Training For Streaming CTC-Trained Automatic Speech Recognition Models
This paper introduces a novel training framework called Focused Discriminative Training (FDT) to further improve streaming word-piece end-to-end (E2E) automatic speech recognition (ASR) models trained using either CTC or an interpolation of CTC and attention-based encoder-decoder (AED) loss.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Optimizing Byte-level Representation for End-to-end ASR
Byte-level representation is often used by large scale multilingual ASR systems when the character set of the supported languages is large.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Approximate Nearest Neighbour Phrase Mining for Contextual Speech Recognition
By including approximate nearest neighbour phrases (ANN-P) in the context list, we encourage the learned representation to disambiguate between similar, but not identical, biasing phrases.
Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios.
Exploring Retraining-Free Speech Recognition for Intra-sentential Code-Switching
To achieve such an ambitious goal, new mechanisms for foreign pronunciation generation and language model (LM) enrichment have been devised.
Frame-level SpecAugment for Deep Convolutional Neural Networks in Hybrid ASR Systems
We demonstrate that f-SpecAugment is more effective than the utterance level SpecAugment for deep CNN based hybrid models.
SNDCNN: Self-normalizing deep CNNs with scaled exponential linear units for speech recognition
The most popular way to train very deep CNNs is to use shortcut connections (SC) together with batch normalization (BN).
Zero-shot Event Detection using Multi-modal Fusion of Weakly Supervised Concepts
Current state-of-the-art systems for visual content analysis require large training sets for each class of interest, and performance degrades rapidly with fewer examples.
