Search Results for author:
Found 24 papers, 0 papers with code
Convolutional Neural Networks for Video Quality Assessment
Moreover, transmission also introduces delays and other distortion types which affect the perceived quality.
Streaming End-to-End Bilingual ASR Systems with Joint Language Identification
Experiments show that for English-Spanish, the bilingual joint ASR-LID architecture matches monolingual ASR and acoustic-only LID accuracies.
Semantic Complexity in End-to-End Spoken Language Understanding
We perform experiments where we vary the semantic complexity of a large, proprietary dataset and show that STI model performance correlates with our semantic complexity measures, such that performance increases as complexity values decrease.
End-to-End Neural Transformer Based Spoken Language Understanding
In this paper, we introduce an end-to-end neural transformer-based SLU model that can predict the variable-length domain, intent, and slots vectors embedded in an audio signal with no intermediate token prediction architecture.
Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding
In this paper, we treat an E2E system as a multi-modal model, with audio and text functioning as its two modalities, and use a cross-modal latent space (CMLS) architecture, where a shared latent space is learned between the `acoustic' and `text' embeddings.
End-to-End Multi-Channel Transformer for Speech Recognition
Transformers are powerful neural architectures that allow integrating different modalities using attention mechanisms.
Sparsification via Compressed Sensing for Automatic Speech Recognition
In the literature, such methods are referred to as sparse pruning.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of the largest of its kind.
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition
We find that tandem training of teacher and student encoders with an inplace encoder distillation outperforms the use of a pre-trained and static teacher transducer.
End-to-End Spoken Language Understanding for Generalized Voice Assistants
End-to-end (E2E) spoken language understanding (SLU) systems predict utterance semantics directly from speech using a single model.
Ranked #10 on
Spoken Language Understanding
on Fluent Speech Commands
(using extra training data)
Multi-Channel Transformer Transducer for Speech Recognition
In this paper, we present a novel speech recognition model, Multi-Channel Transformer Transducer (MCTT), which features end-to-end multi-channel training, low computation cost, and low latency so that it is suitable for streaming decoding in on-device speech recognition.
FANS: Fusing ASR and NLU for on-device SLU
In this paper, we introduce FANS, a new end-to-end SLU model that fuses an ASR audio encoder to a multi-task NLU decoder to infer the intent, slot tags, and slot values directly from a given input audio, obviating the need for transcription.
Ranked #14 on
Spoken Language Understanding
on Fluent Speech Commands
(using extra training data)
Context-Aware Transformer Transducer for Speech Recognition
We also leverage both BLSTM and pretrained BERT based models to encode contextual data and guide the network training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
A neural prosody encoder for end-ro-end dialogue act classification
Dialogue act classification (DAC) is a critical task for spoken language understanding in dialogue systems.
Contextual Adapters for Personalized Speech Recognition in Neural Transducers
Personal rare word recognition in end-to-end Automatic Speech Recognition (E2E ASR) models is a challenge due to the lack of training data.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Sub-8-Bit Quantization Aware Training for 8-Bit Neural Network Accelerator with On-Device Speech Recognition
We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators.
Compute Cost Amortized Transformer for Streaming ASR
We present a streaming, Transformer-based end-to-end automatic speech recognition (ASR) architecture which achieves efficient neural inference through compute cost amortization.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
Very recently, as an alternative to LSTM layers, the Conformer architecture was introduced where the encoder of RNN-T is replaced with a modified Transformer encoder composed of convolutional layers at the frontend and between attention layers.
Sub-8-bit quantization for on-device speech recognition: a regularization-free approach
For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
We augment the MC fusion networks to a conformer transducer model and train it in an end-to-end fashion.
Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition
We present dual-attention neural biasing, an architecture designed to boost Wake Words (WW) recognition and improve inference time latency on speech recognition tasks.
Lookahead When It Matters: Adaptive Non-causal Transformers for Streaming Neural Transducers
Streaming speech recognition architectures are employed for low-latency, real-time applications.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition
Prior approaches typically relied on subword encoders for encoding the bias phrases.
Accelerator-Aware Training for Transducer-Based Speech Recognition
Machine learning model weights and activations are represented in full-precision during training.
