Addressing Text-Dependent Speaker Verification Using Singing Speech

Abstract

The automatic speaker verification (ASV) has achieved significant progress in recent years. However, it is still very challenging to generalize the ASV technologies to new, unknown and spoofing conditions. Most previous studies focused on extracting the speaker information from natural speech. This paper attempts to address the speaker verification from another perspective. The speaker identity information was exploited from singing speech. We first designed and released a new corpus for speaker verification based on singing and normal reading speech. Then, the speaker discrimination was compared and analyzed between natural and singing speech in different feature spaces. Furthermore, the conventional Gaussian mixture model, the dynamic time warping and the state-of-the-art deep neural network were investigated. They were used to build text-dependent ASV systems with different training-test conditions. Experimental results show that the voiceprint information in the singing speech was more distinguishable than the one in the normal speech. More than relative 20% reduction of equal error rate was obtained on both the gender-dependent and independent 1 s-1 s evaluation tasks.

Investigation of Spoken-Language Detection and Classification in Broadcasted Audio Content

“…Moreover, innovative Deep Learning and Convolutional Neural Networks architectures are deployed in this direction [4,5,35] with 2-D input features [7,15]. In addition, several experiments were conducted either on singing voices [18] or in utterance level [19]. Despite the progression in algorithmic level, many related efforts shifted to the development of mechanisms for archiving increased language material [36][37][38][39][40].…”

“…The audio signals were formatted (transcoded) to PCM (Pulse-Code Modulation) Wav files (16-bit depth, 44,100 Hz sample rate). At the same time, the stereo property was discarded, since it could serve only for the music/genre discrimination and not for voice (and language) recognition, as it was thoroughly studied in [16][17][18][19][20].…”

“…Specifically, the first level involves an initial scheme in the radio content, aiming to separate the voice signals of the main speakers (V), the telephone conversations (P) and the music interferences (M), therefore forming the VPM discrimination scheme. It has to be noted that the VPM taxonomy was firstly introduced and examined in [14][15][16][17][18][19][20] for Greek radio broadcasts, to isolate the main voices for validation and indexing purposes. Hence, the adoption of the correspondent VPM scheme in the current work serves as an extension to [14][15][16][17][18][19][20], in the context of generic classification of speech/non-speech radio signals, deriving from an augmented database of multilingual radio broadcasts.…”

“…In this context, new audio recognition and semantic analysis techniques are deployed for General Audio Detection and Classification (GADC) tasks, which are very useful in many multidisciplinary domains [4][5][6][7][8][9][10][11][12][13][14][15][16]. Typical examples include speech recognition and perceptual enhancement [5][6][7][8], speaker indexing and diarization [14][15][16][17][18][19], voice/music detection and discrimination [1][2][3][4][9][10][11][12][13][20][21][22], information retrieval and genre classification of music [23,24], audio-driven alignment of multiple recordings [25,26], sound emotion recognition [27][28][29] and others [10,[30][31][32]. Concerning the media production and broadcasting domain, audio and audio-driven segmentation allow for the implementation of prope...…”

“…Typical examples include speech recognition and perceptual enhancement [5][6][7][8], speaker indexing and diarization [14][15][16][17][18][19], voice/music detection and discrimination [1][2][3][4][9][10][11][12][13][20][21][22], information retrieval and genre classification of music [23,24], audio-driven alignment of multiple recordings [25,26], sound emotion recognition [27][28][29] and others [10,[30][31][32]. Concerning the media production and broadcasting domain, audio and audio-driven segmentation allow for the implementation of proper archiving, thus facilitating content reuse scenarios [1- 3,11,12,[16][17][18][19][20]31]. Besides internal (within the media organization) searching and retrieval, publicity metrics of specific radio stations and programs can be associated with the presence of various audio classes (of both speakers and music species), providing valuable feedback to all involved in the broadcasting process (i.e., producers, advertisers, communication professionals, journalists, etc.)…”