Search Results for author:
Found 11 papers, 6 papers with code
Learning Fine-Grained Controllability on Speech Generation via Efficient Fine-Tuning
As the scale of generative models continues to grow, efficient reuse and adaptation of pre-trained models have become crucial considerations.
Audiobox: Unified Audio Generation with Natural Language Prompts
Research communities have made great progress over the past year advancing the performance of large scale audio generative models for a single modality (speech, sound, or music) through adopting more powerful generative models and scaling data.
Ranked #1 on
Audio Generation
on AudioCaps
Generative Pre-training for Speech with Flow Matching
Generative models have gained more and more attention in recent years for their remarkable success in tasks that required estimating and sampling data distribution to generate high-fidelity synthetic data.
Scaling Speech Technology to 1,000+ Languages
Expanding the language coverage of speech technology has the potential to improve access to information for many more people.
On-demand compute reduction with stochastic wav2vec 2.0
Our results for models pre-trained on 960h Librispeech dataset and fine-tuned on 10h of transcribed data show that using the same stochastic model, we get a smooth trade-off between word error rate (WER) and inference time with only marginal WER degradation compared to the W2V2 and SEW models trained for a specific setting.
Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic model
On Switchboard (300h) we obtain relative improvements of 33% and 35% respectively.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Lattice-Free MMI Adaptation Of Self-Supervised Pretrained Acoustic Models
In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model.
Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Models
We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi's LF-MMI training framework.
Audio and Speech Processing Sound
Fast Transformers with Clustered Attention
This results in a model with linear complexity with respect to the sequence length for a fixed number of clusters.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
Transformers achieve remarkable performance in several tasks but due to their quadratic complexity, with respect to the input's length, they are prohibitively slow for very long sequences.
Ranked #5 on
Offline RL
on D4RL
Out-of-Distribution Detection Using an Ensemble of Self Supervised Leave-out Classifiers
In conjunction with the standard cross-entropy loss, we minimize the novel loss to train an ensemble of classifiers.
