Evaluation of Soft Segment Modeling on a Context Independent Phoneme Classification System
نویسندگان
چکیده
ةــصلاخلا : ُـي ةيساسلأا تاضارتفلاا نم ةلاحلا دادتملا يسدنهلا عيزوتلا ربتع ةراشلأل فوآرام ةجذمن ءادأ نم د ُّ حت يتلا ةيتوص لا . ة يعباتتلا ءاز جلأا جذو منأ نإ ف ،مو معلا ى لعو – تا يئزج كلذ آو ،ةيئاوش علا HMM ى لعو ، يف ةبوعص ةجرد يف ةدا يز ى لإ هرود ب يدؤ ي اً يئزج صقن لا اذ ه زواجتل ،صوصخلا روطلا د يدحتو بيرد ت . جذو من نمض توصلا تايئاصحلال يجيرد تلا ي نمزلا ر يغتلا جرد ن م ل ،ضار تفلاا اذ ه ى لإ ةفاضأ HMM . ريد قت ى لع ةروا جتملا تا يئزجلا ر ثأ جذو منلا ي ف درو ن ثيح ،ة جذمنلل ةد يدج ة قيرط ثحبلا اذ ه ي ف ضرعن ذب ،ةيتوص ةيئزْجُ لآ باسح كلذآو ةفاثكلا نارتقا تلاامتحا ،ةيئزجلا ءاطخلاا َّ دِـض اًتابث رثآأ جذومنلأا نوكي كل تارتيمارابلا نم ددع لقأ مادختساب ىرخأ ىلإ ةيئزجُ نم ريغتلا جلاعيُ كلذآو . مادختساب جذو منلاا اذ ه رابتخا مت ماظن TIMIT ةلقتسملا ةيتوصلا تايئزجلا ماظن ىلع دمتعي يذلا . ةيتوص لا تا يئزجلا فينصت م ت رابتخلاا ءانثا لصتم يفاثآ جذومنأب اهتنراقم مث نمو لولحلا لضفأ ىلإ لصوتلاو اهيلع فرعتلل قرط ةدع مادختساب – جذومنأ رتتسملا فوآرام ) CDHMM .( ردقب اًنسحت جئاتنلا ترهظأ % 10 – 8 جذومناب ةنراقم يتوصلا فرعتلا يف يساسلأا فوآرام .
منابع مشابه
Allophone-based acoustic modeling for Persian phoneme recognition
Phoneme recognition is one of the fundamental phases of automatic speech recognition. Coarticulation which refers to the integration of sounds, is one of the important obstacles in phoneme recognition. In other words, each phone is influenced and changed by the characteristics of its neighbor phones, and coarticulation is responsible for most of these changes. The idea of modeling the effects o...
متن کاملA statistical phonemic segment model for speech recognition based on automatic phonemic segmentation
This paper presents a method of constructing a statistical phonemic segment model (SPSM) for a speech recognition system based on speaker-independent context-independent automatic phonemic segmentation. In our recent research, we proposed the phoneme recognition system using the template matching method with the same segmentation, and confirmed that 5-frame-fixed time sequence of feature vector...
متن کاملAcoustic observation context modeling in segment based speech recognition
This paper describes a novel method that models the correlation between acoustic observations in contiguous speech segments. The basic idea behind the method is that acoustic observations are conditioned not only on the phonetic context but also on the preceding acoustic segment observation. The correlation between consecutive acoustic observations is modeled by polynomial mean trajectory segme...
متن کاملSpeaker Independent Phoneme Classification in Continuous Speech
This paper examines statistical models for phoneme classification. We compare the performance of our phoneme classification system using Gaussian mixture (GMM) phoneme models with systems using hidden Markov phoneme models (HMM). Measurements show that our model’s performance is comparable with HMM models in context independent phoneme classification.
متن کاملPhoneme Classification Using Temporal Tracking of Speech Clusters in Spectro-temporal Domain
This article presents a new feature extraction technique based on the temporal tracking of clusters in spectro-temporal features space. In the proposed method, auditory cortical outputs were clustered. The attributes of speech clusters were extracted as secondary features. However, the shape and position of speech clusters change during the time. The clusters temporally tracked and temporal tra...
متن کامل