Search Results for author:
Found 21 papers, 10 papers with code
Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters
It exploits adapters as the experts and, leveraging the recent Soft MoE method, it relies on a soft assignment between the input tokens and experts to keep the computational time limited.
Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
The common modus operandi of fine-tuning large pre-trained Transformer models entails the adaptation of all their parameters (i. e., full fine-tuning).
Continual Contrastive Spoken Language Understanding
In this paper, we investigate the problem of learning sequence-to-sequence models for spoken language understanding in a class-incremental learning (CIL) setting and we propose COCONUT, a CIL method that relies on the combination of experience replay and contrastive learning.
Training dynamic models using early exits for automatic speech recognition on resource-constrained devices
In self-attention models for automatic speech recognition (ASR), early-exit architectures enable the development of dynamic models capable of adapting their size and architecture to varying levels of computational resources and ASR performance demands.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
An Experimental Review of Speaker Diarization methods with application to Two-Speaker Conversational Telephone Speech recordings
We found that, among all methods considered, EEND-vector clustering (EEND-VC) offers the best trade-off in terms of computing requirements and performance.
Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding
The ability to learn new concepts sequentially is a major weakness for modern neural networks, which hinders their use in non-stationary environments.
End-to-End Integration of Speech Separation and Voice Activity Detection for Low-Latency Diarization of Telephone Conversations
Finally, we also show that the separated signals can be readily used also for automatic speech recognition, reaching performance close to using oracle sources in some configurations.
Improving the Intent Classification accuracy in Noisy Environment
Intent classification is a fundamental task in the spoken language understanding field that has recently gained the attention of the scientific community, mainly because of the feasibility of approaching it with end-to-end neural models.
Scaling strategies for on-device low-complexity source separation with Conv-Tasnet
Given the modular nature of the well-known Conv-Tasnet speech separation architecture, in this paper we consider three parameters that directly control the overall size of the model, namely: the number of residual blocks, the number of repetitions of the separation blocks and the number of channels in the depth-wise convolutions, and experimentally evaluate how they affect the speech separation performance.
An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding
Continual learning refers to a dynamical framework in which a model receives a stream of non-stationary data over time and must adapt to new data while preserving previously acquired knowledge.
Low-complexity acoustic scene classification in DCASE 2022 Challenge
The provided baseline system is a convolutional neural network which employs post-training quantization of parameters, resulting in 46. 5 K parameters, and 29. 23 million multiply-and-accumulate operations (MMACs).
Conversational Speech Separation: an Evaluation Study for Streaming Applications
Continuous speech separation (CSS) is a recently proposed framework which aims at separating each speaker from an input mixture signal in a streaming fashion.
Low-Latency Speech Separation Guided Diarization for Telephone Conversations
In particular, we compare two low-latency speech separation models.
Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?
Generally, models that fuse complementary information from multiple modalities outperform their uni-modal counterparts.
Cross-Modal Knowledge Transfer via Inter-Modal Translation and Alignment for Affect Recognition
For this reason, we aim to improve the performance of uni-modal affect recognition models by transferring knowledge from a better-performing (or stronger) modality to a weaker modality during training.
Learning to Rank Microphones for Distant Speech Recognition
Fully exploiting ad-hoc microphone networks for distant speech recognition is still an open issue.
Robust Latent Representations via Cross-Modal Translation and Alignment
The proposed multi-modal training framework uses cross-modal translation and correlation-based latent space alignment to improve the representations of the weaker modalities.
Compact recurrent neural networks for acoustic event detection on low-energy low-complexity platforms
This paper addresses the application of sound event detection at the edge, by optimizing deep learning techniques on resource-constrained embedded platforms for the IoT.
The Speed Submission to DIHARD II: Contributions & Lessons Learned
This paper describes the speaker diarization systems developed for the Second DIHARD Speech Diarization Challenge (DIHARD II) by the Speed team.
Supervised online diarization with sample mean loss for multi-domain data
Recently, a fully supervised speaker diarization approach was proposed (UIS-RNN) which models speakers using multiple instances of a parameter-sharing recurrent neural network.
Ranked #1 on
Speaker Diarization
on DIHARD II
ConflictNET: End-to-End Learning for Speech-based Conflict Intensity Estimation
Computational paralinguistics aims to infer human emotions, personality traits and behavioural patterns from speech signals.
