I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition

• URL: http://arxiv.org/abs/2407.18058v1
• Date: Thu, 25 Jul 2024 14:15:05 GMT
• Title: I can listen but cannot read: An evaluation of two-tower multimodal systems for instrument recognition
• Authors: Yannis Vasilakis, Rachel Bittner, Johan Pauwels,
• Abstract summary: Music two-tower multimodal systems integrate audio and text modalities into a joint audio-text space. This paper evaluates the inherent zero-shot properties of joint audio-text spaces for the case-study of instrument recognition.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Music two-tower multimodal systems integrate audio and text modalities into a joint audio-text space, enabling direct comparison between songs and their corresponding labels. These systems enable new approaches for classification and retrieval, leveraging both modalities. Despite the promising results they have shown for zero-shot classification and retrieval tasks, closer inspection of the embeddings is needed. This paper evaluates the inherent zero-shot properties of joint audio-text spaces for the case-study of instrument recognition. We present an evaluation and analysis of two-tower systems for zero-shot instrument recognition and a detailed analysis of the properties of the pre-joint and joint embeddings spaces. Our findings suggest that audio encoders alone demonstrate good quality, while challenges remain within the text encoder or joint space projection. Specifically, two-tower systems exhibit sensitivity towards specific words, favoring generic prompts over musically informed ones. Despite the large size of textual encoders, they do not yet leverage additional textual context or infer instruments accurately from their descriptions. Lastly, a novel approach for quantifying the semantic meaningfulness of the textual space leveraging an instrument ontology is proposed. This method reveals deficiencies in the systems' understanding of instruments and provides evidence of the need for fine-tuning text encoders on musical data.

Related papers

• Separate This, and All of these Things Around It: Music Source Separation via Hyperellipsoidal Queries [53.30852012059025]
  Music source separation is an audio-to-audio retrieval task. Recent work in music source separation has begun to challenge the fixed-stem paradigm. We propose the use of hyperellipsoidal regions as queries to allow for an intuitive yet easily parametrizable approach to specifying both the target (location) and its spread.
  arXiv  Detail & Related papers  (2025-01-27T16:13:50Z)
• Disentangling Textual and Acoustic Features of Neural Speech Representations [23.486891834252535]
  We build upon the Information Bottleneck principle to propose a disentanglement framework for complex speech representations. We apply our framework to emotion recognition and speaker identification downstream tasks.
  arXiv  Detail & Related papers  (2024-10-03T22:48:04Z)
• Grammar Induction from Visual, Speech and Text [91.98797120799227]
  This work introduces a novel visual-audio-text grammar induction task (textbfVAT-GI) Inspired by the fact that language grammar exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. We propose a visual-audio-text inside-outside autoencoder (textbfVaTiora) framework, which leverages rich modal-specific and complementary features for effective grammar parsing.
  arXiv  Detail & Related papers  (2024-10-01T02:24:18Z)
• Evaluation of pretrained language models on music understanding [0.0]
  We demonstrate that Large Language Models (LLM) suffer from 1) prompt sensitivity, 2) inability to model negation, and 3) sensitivity towards the presence of specific words. We quantified these properties as a triplet-based accuracy, evaluating the ability to model the relative similarity of labels in a hierarchical ontology. Despite the relatively high accuracy reported, inconsistencies are evident in all six models, suggesting that off-the-shelf LLMs need adaptation to music before use.
  arXiv  Detail & Related papers  (2024-09-17T14:44:49Z)
• Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation [67.89838237013078]
  Named entity recognition (NER) models often struggle with noisy inputs. We propose a more realistic setting in which only noisy text and its NER labels are available. We employ a multi-view training framework that improves robust NER without retrieving text during inference.
  arXiv  Detail & Related papers  (2024-07-26T07:30:41Z)
• On the Possibilities of AI-Generated Text Detection [76.55825911221434]
  We argue that as machine-generated text approximates human-like quality, the sample size needed for detection bounds increases. We test various state-of-the-art text generators, including GPT-2, GPT-3.5-Turbo, Llama, Llama-2-13B-Chat-HF, and Llama-2-70B-Chat-HF, against detectors, including oBERTa-Large/Base-Detector, GPTZero.
  arXiv  Detail & Related papers  (2023-04-10T17:47:39Z)
• Combining Automatic Speaker Verification and Prosody Analysis for Synthetic Speech Detection [15.884911752869437]
  We present a novel approach for synthetic speech detection, exploiting the combination of two high-level semantic properties of the human voice. On one side, we focus on speaker identity cues and represent them as speaker embeddings extracted using a state-of-the-art method for the automatic speaker verification task. On the other side, voice prosody, intended as variations in rhythm, pitch or accent in speech, is extracted through a specialized encoder.
  arXiv  Detail & Related papers  (2022-10-31T11:03:03Z)
• ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition [100.30565531246165]
  Speech recognition systems require dataset-specific tuning. This tuning requirement can lead to systems failing to generalise to other datasets and domains. We introduce the End-to-end Speech Benchmark (ESB) for evaluating the performance of a single automatic speech recognition system.
  arXiv  Detail & Related papers  (2022-10-24T15:58:48Z)
• Analysis of Joint Speech-Text Embeddings for Semantic Matching [3.6423306784901235]
  We study a joint speech-text embedding space trained for semantic matching by minimizing the distance between paired utterance and transcription inputs. We extend our method to incorporate automatic speech recognition through both pretraining and multitask scenarios.
  arXiv  Detail & Related papers  (2022-04-04T04:50:32Z)
• Audio-text Retrieval in Context [24.38055340045366]
  In this work, we investigate several audio features as well as sequence aggregation methods for better audio-text alignment. We build our contextual audio-text retrieval system using pre-trained audio features and a descriptor-based aggregation method. With our proposed system, a significant improvement has been achieved on bidirectional audio-text retrieval, on all metrics including recall, median and mean rank.
  arXiv  Detail & Related papers  (2022-03-25T13:41:17Z)
• Improving Machine Reading Comprehension with Contextualized Commonsense Knowledge [62.46091695615262]
  We aim to extract commonsense knowledge to improve machine reading comprehension. We propose to represent relations implicitly by situating structured knowledge in a context. We employ a teacher-student paradigm to inject multiple types of contextualized knowledge into a student machine reader.
  arXiv  Detail & Related papers  (2020-09-12T17:20:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.