Speech Sentiment Analysis via Pre-Trained Features from End-to-End ASR Models

Zhiyun Lu · Liangliang Cao · Yu Zhang · Chung‐Cheng Chiu · James Fan

79 citations0/0 files storedIEEE International Conference on Acoustics Speech and Signal Processing

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Emotion and Mood Recognition Speech Recognition and Synthesis Sentiment Analysis and Opinion Mining

Abstract

In this paper, we propose to use pre-trained features from end-to-end ASR models to solve speech sentiment analysis as a down-stream task. We show that end-to-end ASR features, which integrate both acoustic and text information from speech, achieve promising results. We use RNN with self-attention as the sentiment classifier, which also provides an easy visualization through attention weights to help interpret model predictions. We use well benchmarked IEMOCAP dataset and a new large-scale speech sentiment dataset SWBD-sentiment for evaluation. Our approach improves the-state-of-the-art accuracy on IEMOCAP from 66.6% to 71.7%, and achieves an accuracy of 70.10% on SWBD-sentiment with more than 49,500 utterances.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 79 citations exist upstream.

References

2008IEMOCAP: interactive emotional dyadic motion capture database 2018End-to-End Speech Emotion Recognition Using Deep Neural Networks 2019Speech Emotion Classification Using Attention-Based LSTM 2018An Attention Pooling Based Representation Learning Method for Speech Emotion Recognition 2018Multimodal Affective Analysis Using Hierarchical Attention Strategy with Word-Level Alignment 2019Speech Emotion Recognition Using Capsule Networks 2018Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts 2019Attention-augmented End-to-end Multi-task Learning for Emotion Prediction from Speech

Cited by

2021Emotion Recognition by Fusing Time Synchronous and Time Asynchronous Representations

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.