Reducing Model Complexity for DNN Based Large-Scale Audio Classification

Tan Lee; Yuzhong Wu

RECORD

Reducing Model Complexity for DNN Based Large-Scale Audio Classification

Yuzhong Wu, Tan Lee

Sound · Submitted 1 Nov 2017

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim It is shown that the simplified CNN model has only 1/22 model parameters of the original model, with only a slight degradation of performance.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 6,098 input tokens.

What the abstract itself states, as probabilities: claims first 0.03 · states limitation 0.67 · human participants 0.15 · controlled comparison 0.63 · randomized assignment 0.02 · states quantitative result 0.98 · compares with prior results 0.86 · mentions code or data availability 0.02.

The abstract, sentence by sentence

arXiv listing abstract v2. Results and the main claim are underlined; show every role.

Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database. AudioSet comprises 2 millions of audio samples from YouTube, which are human-annotated with 527 sound category labels. Audio classification experiments with the balanced training set and the evaluation set of AudioSet are carried out by applying different types of neural network models. The classification performance and the model complexity of these models are compared and analyzed. While the CNN models show better performance than MLP and RNN, its model complexity is relatively high and undesirable for practical use. We propose two different strategies that aim at constructing low-dimensional embedding feature extractors and hence reducing the number of model parameters. It is shown that the simplified CNN model has only 1/22 model parameters of the original model, with only a slight degradation of performance.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	Audio classification is the task of identifying the sound categories that are associated with a given audio signal.	background 1.00	0.04	0.01	asserted 0.99
s1	This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database.	contribution 0.95	0.73	0.03	asserted 0.96
s2	AudioSet comprises 2 millions of audio samples from YouTube, which are human-annotated with 527 sound category labels.	background 0.57	0.08	0.02	asserted 1.00
s3	Audio classification experiments with the balanced training set and the evaluation set of AudioSet are carried out by applying different types of neural network models.	method 0.97	0.91	0.02	asserted 0.99
s4	The classification performance and the model complexity of these models are compared and analyzed.	method 0.80	0.89	0.05	asserted 0.91
s5	While the CNN models show better performance than MLP and RNN, its model complexity is relatively high and undesirable for practical use.	result 0.67	0.82	0.11	asserted 1.00
s6	We propose two different strategies that aim at constructing low-dimensional embedding feature extractors and hence reducing the number of model parameters.	contribution 0.89	0.90	0.16	asserted 0.92
s7	It is shown that the simplified CNN model has only 1/22 model parameters of the original model, with only a slight degradation of performance.	result 1.00	0.94	0.71	asserted 1.00

What kind of paper the classifier reports this is: method or tool 0.82 · evidence from observation or experiment 0.88.

What was examined, and what was not

sources read

arXiv listing abstract v2

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

Audio classification is the task of identifying the sound categories that are associated with a given audio signal. This paper presents an investigation on large-scale audio classification based on the recently released AudioSet database. AudioSet comprises 2 millions of audio samples from YouTube, which are human-annotated with 527 sound category labels. Audio classification experiments with the balanced training set and the evaluation set of AudioSet are carried out by applying different types of neural network models. The classification performance and the model complexity of these models are compared and analyzed. While the CNN models show better performance than MLP and RNN, its model complexity is relatively high and undesirable for practical use. We propose two different strategies that aim at constructing low-dimensional embedding feature extractors and hence reducing the number of model parameters. It is shown that the simplified CNN model has only 1/22 model parameters of the original model, with only a slight degradation of performance.

Human review

How Pith checks papers → · Full audit of this paper →

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.