Azure Cognitive - Speech Recognition Python

Text Dependent Recognition.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "f87e24de",
   "metadata": {},
   "outputs": [],
   "source": [
    "import http.client\n",
    "import json"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "392a5695",
   "metadata": {},
   "source": [
    "# Create Profile"
   ]
  },
  {
   "cell_type": "raw",
   "id": "02e4fa96",
   "metadata": {},
   "source": [
    "POST {Endpoint}/speaker/verification/v2.0/text-dependent/profiles"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "5ef33de4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"remainingEnrollmentsCount\":3,\"locale\":\"en-us\",\"createdDateTime\":\"2021-08-12T09:35:09.465Z\",\"enrollmentStatus\":\"Enrolling\",\"modelVersion\":null,\"profileId\":\"506b52f6-8fe9-44b9-a420-be200880e2a1\",\"lastUpdatedDateTime\":null,\"enrollmentsCount\":0,\"enrollmentsLength\":0.0,\"enrollmentsSpeechLength\":0.0}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0',\n",
    "    'Content-type': 'application/json'}\n",
    "\n",
    "foo = {'locale': 'en-us'}\n",
    "json_data = json.dumps(foo)\n",
    "\n",
    "conn.request(method='POST', url='/speaker/verification/v2.0/text-dependent/profiles', \n",
    "             body=json_data, headers=headers)\n",
    "response = conn.getresponse().read().decode()\n",
    "conn.close()\n",
    "\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "1691c361",
   "metadata": {},
   "outputs": [],
   "source": [
    "profileId = json.loads(response)[\"profileId\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5164d435",
   "metadata": {},
   "source": [
    "# ENROLL PROFILE\n",
    "In current version of text-dependent speaker verification API, we provide 10 English phrases for the speakers to choose from.\n",
    "- I am going to make him an offer he cannot refuse.\n",
    "Houston we have had a problem.\n",
    "- My voice is my passport verify me.\n",
    "- Apple juice tastes funny after toothpaste.\n",
    "- You can get in without your password.\n",
    "- You can activate security system now.\n",
    "- My voice is stronger than passwords.\n",
    "- My password is not your business.\n",
    "- My name is unknown to you.\n",
    "- Be yourself everyone else is already taken"
   ]
  },
  {
   "cell_type": "raw",
   "id": "e2f1871c",
   "metadata": {},
   "source": [
    "POST {Endpoint}/speaker/verification/v2.0/text-dependent/profiles/{profileId}/enrollments"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9154bf01",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "'Speech Services - Quickstart.ipynb'   phrase-record1.wav   settings.xml\r\n",
      "'Text Dependent Recognition.ipynb'     phrase-record2.wav   verify.wav\r\n",
      "'Text Independent Recognition.ipynb'   phrase-record3.wav\r\n",
      " audio\t\t\t\t       record.wav\r\n"
     ]
    }
   ],
   "source": [
    "!ls"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "c4265b1c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"remainingEnrollmentsCount\":2,\"passPhrase\":\"my voice is stronger than passwords\",\"profileId\":\"506b52f6-8fe9-44b9-a420-be200880e2a1\",\"enrollmentStatus\":\"Enrolling\",\"enrollmentsCount\":1,\"enrollmentsLength\":4.21,\"enrollmentsSpeechLength\":2.87,\"audioLength\":4.21,\"audioSpeechLength\":2.87}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "with open('phrase-record1.wav', 'rb') as data:\n",
    "    conn.request(method='POST', \n",
    "                url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}/enrollments?ignoreMinLength=true', \n",
    "                body=data, headers=headers)\n",
    "    response = conn.getresponse().read().decode()\n",
    "    conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2bb4cc4e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"remainingEnrollmentsCount\":1,\"passPhrase\":\"my voice is stronger than passwords\",\"profileId\":\"506b52f6-8fe9-44b9-a420-be200880e2a1\",\"enrollmentStatus\":\"Enrolling\",\"enrollmentsCount\":2,\"enrollmentsLength\":7.65,\"enrollmentsSpeechLength\":5.3,\"audioLength\":3.44,\"audioSpeechLength\":2.43}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "with open('phrase-record2.wav', 'rb') as data:\n",
    "    conn.request(method='POST', \n",
    "                url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}/enrollments?ignoreMinLength=true', \n",
    "                body=data, headers=headers)\n",
    "    response = conn.getresponse().read().decode()\n",
    "    conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "0f7744d9",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"remainingEnrollmentsCount\":0,\"passPhrase\":\"my voice is stronger than passwords\",\"profileId\":\"506b52f6-8fe9-44b9-a420-be200880e2a1\",\"enrollmentStatus\":\"Enrolled\",\"enrollmentsCount\":3,\"enrollmentsLength\":11.49,\"enrollmentsSpeechLength\":7.6,\"audioLength\":3.84,\"audioSpeechLength\":2.3}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "with open('phrase-record3.wav', 'rb') as data:\n",
    "    conn.request(method='POST', \n",
    "                url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}/enrollments?ignoreMinLength=true', \n",
    "                body=data, headers=headers)\n",
    "    response = conn.getresponse().read().decode()\n",
    "    conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7847bc1",
   "metadata": {},
   "source": [
    "# LIST PROFILES"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "9b585660",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"profiles\":[{\"remainingEnrollmentsCount\":3,\"locale\":\"en-us\",\"createdDateTime\":\"2021-08-10T15:26:47.191Z\",\"enrollmentStatus\":\"Enrolling\",\"modelVersion\":null,\"profileId\":\"0ae74e3c-3c1b-433b-a6fb-11826f8f69f9\",\"lastUpdatedDateTime\":null,\"enrollmentsCount\":0,\"enrollmentsLength\":0.0,\"enrollmentsSpeechLength\":0.0},{\"remainingEnrollmentsCount\":0,\"locale\":\"en-us\",\"createdDateTime\":\"2021-08-12T09:35:09.465Z\",\"enrollmentStatus\":\"Enrolled\",\"modelVersion\":\"2019-11-01\",\"profileId\":\"506b52f6-8fe9-44b9-a420-be200880e2a1\",\"lastUpdatedDateTime\":\"08/12/2021 09:49:07\",\"enrollmentsCount\":3,\"enrollmentsLength\":11.49,\"enrollmentsSpeechLength\":0.0}],\"@nextLink\":\"\"}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "conn.request(method='GET', url='/speaker/verification/v2.0/text-dependent/profiles?$top=10', \n",
    "             headers=headers)\n",
    "response = conn.getresponse().read().decode()\n",
    "conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "d8b09aad",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(json.loads(response)[\"profiles\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "01a23e8a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'506b52f6-8fe9-44b9-a420-be200880e2a1'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "profileId"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4a4ec125",
   "metadata": {},
   "source": [
    "# VERIFY PROFILE"
   ]
  },
  {
   "cell_type": "raw",
   "id": "6df6cb28",
   "metadata": {},
   "source": [
    "POST {Endpoint}/speaker/verification/v2.0/text-dependent/profiles/{profileId}/verify"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "d9f29b76",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{\"recognitionResult\":\"Accept\",\"score\":0.5509841442108154}\n"
     ]
    }
   ],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "with open('phrase-verify.wav', 'rb') as data:\n",
    "    conn.request(method='POST', \n",
    "                url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}/verify', \n",
    "                body=data, headers=headers)\n",
    "    response = conn.getresponse().read().decode()\n",
    "    conn.close()\n",
    "    print(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3774b422",
   "metadata": {},
   "source": [
    "# DELETE PROFILE"
   ]
  },
  {
   "cell_type": "raw",
   "id": "12795b0d",
   "metadata": {},
   "source": [
    "DELETE {Endpoint}/speaker/verification/v2.0/text-dependent/profiles/{profileId}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2abfe4a3",
   "metadata": {},
   "outputs": [],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "conn.request(method='DELETE', url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}', \n",
    "             headers=headers)\n",
    "response = conn.getresponse().read().decode()\n",
    "conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "95bca90a",
   "metadata": {},
   "source": [
    "# RESET PROFILE"
   ]
  },
  {
   "cell_type": "raw",
   "id": "f57d8c6b",
   "metadata": {},
   "source": [
    "POST {Endpoint}/speaker/verification/v2.0/text-dependent/profiles/{profileId}/reset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f7db2350",
   "metadata": {},
   "outputs": [],
   "source": [
    "conn = http.client.HTTPSConnection('westus.api.cognitive.microsoft.com')\n",
    "\n",
    "headers = {'Ocp-Apim-Subscription-Key': 'f92e7479ee9f4e1ca9ba46c32e5644a0'}\n",
    "\n",
    "conn.request(method='DELETE', url=f'/speaker/verification/v2.0/text-dependent/profiles/{profileId}/reset', \n",
    "             headers=headers)\n",
    "response = conn.getresponse().read().decode()\n",
    "conn.close()\n",
    "print(response)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7027b08d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c3af57a9",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.8.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}