Babble Noise: Modeling, Analysis, and Applications

Krishnamurthy, Nitish; Hansen, John H. L.

doi:10.1109/tasl.2009.2015084

Cited by 66 publications

(50 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Three noise samples from this dataset were used as the car, street and office noise samples. Krishnamurthy and Hansen [19] distinguished three categories of babble noise based on the number of speakers: competing speaker; babble; and large-crowd. Competing speaker was defined as having only two speakers.…”

Section: A Background Noisementioning

confidence: 99%

See 1 more Smart Citation

TCD-VoIP, a research database of degraded speech for assessing quality in VoIP applications

Harte

Gillen

Hines³

2015

2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

Abstract-There are many types of degradation which can occur in Voice over IP calls. Degradations which occur independently of the codec, hardware, or network in use are the focus of this paper. The development of new quality metrics for modern communication systems depends heavily on the availability of suitable test and development data with subjective quality scores. A new dataset of VoIP degradations (TCD-VoIP) has been created and is presented in this paper. The dataset contains speech samples with a range of common VoIP degradations, and the corresponding set of subjective opinion scores from 24 listeners. The dataset is publicly available.

show abstract

Section: A Background Noisementioning

confidence: 99%

“…As explained by Krishnamurthy and Hansen [19], real background noise is usually made up of conversations. In a conversation, both speakers rarely speak at the same time.…”

Section: B Competing Speakersmentioning

confidence: 99%

TCD-VoIP, a research database of degraded speech for assessing quality in VoIP applications

Harte

Gillen

Hines³

2015

2015 Seventh International Workshop on Quality of Multimedia Experience (QoMEX)

View full text Add to dashboard Cite

show abstract

“…These noisy speech examples are at different input SNRs equal to 1dB, 5dB, 10dB and 15dB and signal with improved SNR is obtained at output. Speech babble is one of the most challenging noise interference for all speech systems [14]. Listener suffers from babble noise when user is in crowd or multi talkers are present.…”

Section: Simulation Resultsmentioning

confidence: 99%

A Novel Approach of Speech Enhancement by Implementing Cellular Automata Algorithm

Adhav¹,

Kene²

2016

IJCA

View full text Add to dashboard Cite

The main purpose of speech enhancement technique is to eliminate the background noise from speech signal to improve the quality of the speech signal. Speech signal is often corrupted by additive background noise like train noise, market noise etc. In such noisy environment listening at the end user is very difficult. This paper presents speech enhancement method using Cellular Automata (CA) algorithm. Based on Peak Signal to Noise Ratio and Mean Square Error criterion the system evaluate the amount of surrounding noise present in speech. The proposed algorithm helps to improve the quality of speech signal at the listener end.

show abstract

“…The two currently accepted models of speech babble are the overlap of multiple conversations [12] and the overlap of individual speakers [20]. The differences in the models stem from the interactions of the speakers comprising the babble.…”

Section: Babble Noise and Associated Modelsmentioning

confidence: 99%

“…Figure 1 shows the comparison of the two above-stated models in terms of the probability of different number of active speakers at any one time [12].…”

Section: Babble Noise and Associated Modelsmentioning

confidence: 99%

Visualization of Babble–Speech Interactions Using Andrews Curves

Atkins

Sharma

2015

Circuits Syst Signal Process

View full text Add to dashboard Cite

Visualizing multidimensional data such as the mel frequency cepstral coefficients (MFCCs) proves difficult, especially when the number of dimensions is greater than 3. As a result, it becomes extremely difficult to spot trends in high-dimensional signal interactions. Andrews curves seam to aid in the process of performing graphical analysis of high-dimensional data. This study examines the properties of the babble in the feature domain as well as the effect of the babble noise on the MFCCs of clean speech. Experiments have been conducted using two babble models: the overlapping conversation model and the overlapping speaker model. The purpose of this paper was to provide an insight into the effect of the babble noise on the first thirteen MFCCs of clean speech through the use of Andrews curves. The investigations of this paper give a visual comparison of the signals to expose trends, which the conventional visualization methods do not. The use of Andrews curves not only allows the signal to be observed, but also allows for a statistical comparisons between signals. With a better understanding of the difference between the models, it would be possible to develop systems, which are more robust in babble-corrupted environment.

show abstract

Babble Noise: Modeling, Analysis, and Applications

Cited by 66 publications

References 15 publications

TCD-VoIP, a research database of degraded speech for assessing quality in VoIP applications

TCD-VoIP, a research database of degraded speech for assessing quality in VoIP applications

A Novel Approach of Speech Enhancement by Implementing Cellular Automata Algorithm

Visualization of Babble–Speech Interactions Using Andrews Curves

Contact Info

Product

Resources

About